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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 97854
    Prev
    Next
    INDEX
    Explanations

    the term "key" and its related phrases indicating importance or significance

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

    key aspect or differentiator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     queſta
    -0.56
     ModelExpression
    -0.55
    NameInMap
    -0.46
     gratu
    -0.45
     nyelven
    -0.44
    ItemGroup
    -0.44
     gọn
    -0.43
    ſchen
    -0.43
    astéro
    -0.43
     IndexPath
    -0.43
    POSITIVE LOGITS
     key
    0.71
    🔑
    0.60
     Schlüssel
    0.59
    Key
    0.57
     Key
    0.55
     anahtar
    0.53
    key
    0.52
     keys
    0.50
     klucz
    0.47
    关键
    0.47
    Activations Density 0.011%

    No Known Activations