© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101961
    Prev
    Next
    INDEX
    Explanations

    elements related to data analysis and structure in backend programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The marked text often shows code syntax elements like variable references (this.property), language keywords, operators (&&, .), and programming constructs like function calls (method(parameter)), especially in contexts involving programming languages, database queries, and string concatenation operations.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     społecz
    -0.39
     פני
    -0.35
     Erde
    -0.30
     inspirasi
    -0.29
     médicale
    -0.29
     lectores
    -0.29
    ROOT
    -0.29
     pravi
    -0.29
     doigts
    -0.29
     humaine
    -0.29
    POSITIVE LOGITS
    IntoConstraints
    1.04
    Personendaten
    0.89
    ChildScrollView
    0.81
    tagHelperRunner
    0.80
    ConstraintMaker
    0.77
     الرياضيه
    0.76
    #+#
    0.75
     AssemblyCulture
    0.74
     defStyleAttr
    0.73
     الحره
    0.72
    Activations Density 0.220%

    No Known Activations