© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 15201
    Prev
    Next
    INDEX
    Explanations

    technical jargon and terms related to command-line operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -1.00
     kasarigan
    -0.74
    DockStyle
    -0.69
     nakalista
    -0.68
    IntoConstraints
    -0.67
    ScopeManager
    -0.64
     intptr
    -0.63
     nahilalakip
    -0.63
    tvguidetime
    -0.62
     setuptools
    -0.59
    POSITIVE LOGITS
     line
    4.41
    line
    3.80
     Line
    3.78
    Line
    3.55
     LINE
    3.39
     lines
    3.32
    LINE
    3.14
     Lines
    2.88
    lines
    2.84
     línea
    2.76
    Activations Density 0.748%

    No Known Activations