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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 845
    Prev
    Next
    INDEX
    Explanations

    phrases indicating examples or descriptions related to specific concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    typical examples or possibilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     &___
    -0.44
    ckså
    -0.44
    ostante
    -0.43
     gwaran
    -0.39
    Kontrola
    -0.39
     istnieje
    -0.39
    Cyfeiriadau
    -0.38
     zewnętrzne
    -0.38
    tershire
    -0.38
    uteen
    -0.38
    POSITIVE LOGITS
     typical
    0.95
    typical
    0.83
     Typical
    0.81
    Typical
    0.79
     typically
    0.74
    典型
    0.69
     typique
    0.69
     típico
    0.68
     typ
    0.68
    典型的
    0.65
    Activations Density 0.088%

    No Known Activations