© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 11939
    Prev
    Next
    INDEX
    Explanations

    directives and guidance regarding user actions and responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Salut
    -0.48
    umum
    -0.47
    一部
    -0.46
     tvar
    -0.45
     adatt
    -0.45
    らせて
    -0.43
     adapté
    -0.42
    <eos>
    -0.42
     spoor
    -0.42
    force
    -0.41
    POSITIVE LOGITS
    новништво
    0.81
    вгений
    0.79
    AddHtmlAttribute
    0.76
    égard
    0.74
     مرئيه
    0.73
     getItemCount
    0.72
    getWriter
    0.71
     فريبيس
    0.70
    archiviato
    0.70
     onPostExecute
    0.69
    Activations Density 0.337%

    No Known Activations