© 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. 18-GEMMASCOPE-RES-16K
    11. 8836
    Prev
    Next
    INDEX
    Explanations

    instances of legal or regulatory language

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

    Code and transcripts

    np_acts-logits-general · gemini-2.0-flash

    many millilitres, umber of, another aspect, identified patients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.89
    ImageContext
    -0.86
    IsMutable
    -0.84
    ^(@)
    -0.83
     NgModule
    -0.83
     estekak
    -0.83
     ModelRenderer
    -0.82
     PSN
    -0.82
     AttributeSet
    -0.81
     Efq
    -0.81
    POSITIVE LOGITS
    ↵↵
    1.20
    ↵
    0.99
    <em>
    0.96
    <eos>
    0.95
    ↵↵↵
    0.92
    <strong>
    0.89
    </em>
    0.81
     The
    0.81
    </sub>
    0.78
    </strong>
    0.77
    Activations Density 0.029%

    No Known Activations