Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 7162
    Prev
    Next
    INDEX
    Explanations

    structured data or formalized presentations

    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
    ngua
    -0.55
    PreferredItem
    -0.55
    iläum
    -0.51
    InitStruct
    -0.50
     te
    -0.49
    ServletException
    -0.49
     effects
    -0.49
    Neo
    -0.48
    </b>
    -0.47
     jspb
    -0.47
    POSITIVE LOGITS
    SBATCH
    0.69
     gioielli
    0.68
    ArgsConstructor
    0.64
     kjent
    0.63
     desglose
    0.63
     onData
    0.62
    NSIndexPath
    0.62
    новништво
    0.61
    الحياه
    0.61
     précédents
    0.60
    Activations Density 0.296%

    No Known Activations