© 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. 20-GEMMASCOPE-RES-16K
    11. 16230
    Prev
    Next
    INDEX
    Explanations

    conversational phrases and informal transitions commonly used in spoken language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "So" at the start of sentences

    np_acts-logits-general · gemini-2.0-flash

    So followed by continuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.91
    migrationBuilder
    -0.91
    DispatchToProps
    -0.84
    ();)
    -0.81
     noqa
    -0.80
     AssemblyCompany
    -0.79
     الحره
    -0.78
    ]')
    -0.78
    },[])
    -0.77
     Roskov
    -0.77
    POSITIVE LOGITS
    ,
    0.82
    oner
    0.64
     basically
    0.59
     what
    0.58
     here
    0.58
     how
    0.55
     Here
    0.54
     glad
    0.53
    how
    0.52
    Here
    0.52
    Activations Density 0.075%

    No Known Activations