© 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. 8-GEMMASCOPE-RES-16K
    6. 7852
    Prev
    Next
    INDEX
    Explanations

    references to data ownership and user consent

    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
     sitten
    -0.42
     kropp
    -0.40
     konten
    -0.39
     pembunuhan
    -0.36
    setContent
    -0.36
     auriculares
    -0.36
    spec
    -0.35
     przedsiębior
    -0.35
     Be
    -0.34
     menghubungi
    -0.34
    POSITIVE LOGITS
    AndEndTag
    1.23
    MigrationBuilder
    1.19
     HasFactory
    0.94
    MLLoader
    0.90
     виправивши
    0.88
     propOrder
    0.86
     صوتيه
    0.85
    DockStyle
    0.85
    下载附件
    0.81
    تقاوى
    0.81
    Activations Density 0.468%

    No Known Activations