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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 11183
    Prev
    Next
    INDEX
    Explanations

    structured programming constructs and data handling operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    diano
    -0.50
     صوتيه
    -0.47
    </h3>
    -0.45
    zulegen
    -0.45
     already
    -0.45
     už
    -0.44
     deven
    -0.43
     cres
    -0.43
     כבר
    -0.42
    förm
    -0.42
    POSITIVE LOGITS
    IntoConstraints
    0.74
     doInBackground
    0.70
     itſelf
    0.69
    Portale
    0.67
     StringTokenizer
    0.65
    guenos
    0.65
     NDL
    0.65
     pleaſure
    0.64
     wikipagina
    0.64
    AxisAlignment
    0.62
    Activations Density 0.034%

    No Known Activations