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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 5854
    Prev
    Next
    INDEX
    Explanations

    phrases reflecting vague descriptions and generalizations

    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
     وتسجيلات
    -0.63
     Româ
    -0.57
    Selbst
    -0.56
    eddable
    -0.55
    rewsbury
    -0.55
    httphttps
    -0.55
     ModelExpression
    -0.54
    JspWriter
    -0.54
    المكان
    -0.53
    Double
    -0.53
    POSITIVE LOGITS
     vague
    1.01
     vaguely
    0.94
    openzeppelin
    0.67
     vagu
    0.61
     vagas
    0.60
     vagues
    0.59
     general
    0.58
    AndEndTag
    0.58
     vaga
    0.53
    ague
    0.50
    Activations Density 0.415%

    No Known Activations