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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 15582
    Prev
    Next
    INDEX
    Explanations

    specific programming constructs and entities, particularly focusing on skills and related properties in a structured data context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteTagHelper
    -1.10
    IntoConstraints
    -0.96
    rungsseite
    -0.95
     propOrder
    -0.92
    EndGlobalSection
    -0.90
    ReusableCell
    -0.89
    )");
    -0.88
     autorytatywna
    -0.87
    ConstraintMaker
    -0.86
    ftagPool
    -0.84
    POSITIVE LOGITS
     details
    0.46
     model
    0.44
    ApiModel
    0.43
    vett
    0.43
    ADOS
    0.42
     micros
    0.41
     essence
    0.41
    _
    0.41
    舶
    0.40
    Data
    0.40
    Activations Density 0.328%

    No Known Activations