© 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. 7-GEMMASCOPE-RES-16K
    6. 14525
    Prev
    Next
    INDEX
    Explanations

    specific types of data related to statistics and metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.76
     ApJ
    -0.69
    
    -0.59
    /*
    -0.57
    endpush
    -0.54
    });*/
    -0.54
    --*/
    -0.51
    };*/
    -0.51
    <>());
    -0.50
    cstdio
    -0.50
    POSITIVE LOGITS
    StructEnd
    1.11
    contentLoaded
    0.91
    WithIOException
    0.91
    Geplaatst
    0.87
    webElementXpaths
    0.85
    IsMutable
    0.83
    principalColumn
    0.81
    adpleegd
    0.77
    IonicModule
    0.77
    FunctionFlags
    0.76
    Activations Density 2.810%

    No Known Activations