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. 107982
    Prev
    Next
    INDEX
    Explanations

    references to mitochondrial genomes and their characteristics

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

    mtDNA and mitochondrial genomes

    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
    KommentareTeilen
    -0.78
     ModelExpression
    -0.75
     AppCompatTheme
    -0.69
     AssemblyTitle
    -0.66
    ftagPool
    -0.64
    InjectAttribute
    -0.64
    SharedCtor
    -0.61
    OCCURRED
    -0.60
    PRNewswire
    -0.59
    цезда
    -0.59
    POSITIVE LOGITS
     estrecha
    0.34
     psicológica
    0.31
     turística
    0.30
     extranjera
    0.29
     telefónica
    0.29
    éndole
    0.29
     digo
    0.28
     baterías
    0.28
    éndolo
    0.27
     conductas
    0.27
    Activations Density 0.478%

    No Known Activations