© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 12443
    Prev
    Next
    INDEX
    Explanations

    special formatting or symbols used in technical documents

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

    Text inside brackets or parentheses followed by brackets

    np_acts-logits-general · gemini-2.0-flash

    closing brackets or parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     useDispatch
    -0.52
    -0.52
     labor
    -0.47
     emb
    -0.44
     cit
    -0.43
    ્ર
    -0.43
    stris
    -0.42
     Northwest
    -0.42
     ser
    -0.42
     Pe
    -0.42
    POSITIVE LOGITS
    ]>
    0.84
    ات
    0.83
     $]$
    0.82
    PrototypeOf
    0.80
     financières
    0.78
    _]
    0.75
    }]
    0.72
    _[
    0.71
    })]
    0.71
     présidentielle
    0.70
    Activations Density 0.663%

    No Known Activations