© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 8719
    Prev
    Next
    INDEX
    Explanations

    technical terms or expressions related to computational processes and programming concepts

    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
     autorytatywna
    -0.73
    tvguidetime
    -0.67
    ConstraintMaker
    -0.66
    .";
    
    -0.62
    CppMethod
    -0.61
     gyhoeddwyd
    -0.59
    ԁ
    -0.59
    !</
    -0.57
    ).</
    -0.56
     ErrIntOverflow
    -0.54
    POSITIVE LOGITS
    __
    2.67
     __
    2.52
    .__
    1.92
    (__
    1.75
    ___
    1.69
    )__
    1.67
    ____
    1.61
     (__
    1.56
     "__
    1.52
    __.
    1.52
    Activations Density 0.339%

    No Known Activations