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
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 8361
    Prev
    Next
    INDEX
    Explanations

    references to specific items or categories, particularly in crafting, programming, and discussions related to civil engineering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Erscheinung
    -0.48
     slä
    -0.46
    lemented
    -0.43
    geral
    -0.42
     praça
    -0.42
     encantan
    -0.41
     Wikimedijinoj
    -0.41
     stationnement
    -0.40
     Vordergrund
    -0.40
     complement
    -0.40
    POSITIVE LOGITS
     consultato
    0.61
    CharField
    0.54
     pon
    0.50
    Дереккөздер
    0.48
     drag
    0.47
     PIN
    0.47
    CppCodeGen
    0.46
    istoitu
    0.45
    PIN
    0.44
     Druid
    0.44
    Activations Density 1.844%

    No Known Activations