© 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. 8-GEMMASCOPE-RES-16K
    11. 1749
    Prev
    Next
    INDEX
    Explanations

    features related to numerical data and variables in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    springframework
    -0.63
    ()]);
    -0.63
    ]<<
    -0.59
    },[])
    -0.58
    ]<<"
    -0.56
    ')";
    -0.54
    ])));
    -0.54
     ***!
    -0.53
    \}\\
    -0.53
    complexContent
    -0.53
    POSITIVE LOGITS
    ViewFeatures
    0.96
    IntoConstraints
    0.94
    StructEnd
    0.82
    Tembelea
    0.79
    ModelSerializer
    0.65
    xffffff
    0.64
    ChildScrollView
    0.64
     snippetHide
    0.63
    SharedCtor
    0.62
    addPreferredGap
    0.60
    Activations Density 0.549%

    No Known Activations