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. 7-GEMMASCOPE-RES-16K
    6. 4768
    Prev
    Next
    INDEX
    Explanations

    lines or fragments of text with structured, potentially tabular data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     it
    -0.49
     my
    -0.47
      
    -0.45
     I
    -0.45
    -
    -0.45
    hos
    -0.45
     so
    -0.45
     —
    -0.45
    لوب
    -0.44
    .
    -0.44
    POSITIVE LOGITS
    +#+
    1.11
    verwijspagina
    1.08
     Majefty
    1.04
     ſche
    0.99
     pleaſure
    0.99
     Reſ
    0.95
     occaf
    0.95
     Jefus
    0.95
    はじめに
    0.95
     ſmall
    0.95
    Activations Density 0.921%

    No Known Activations