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. 7164
    Prev
    Next
    INDEX
    Explanations

    instances of the word "up" in various forms or contexts

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

    breaking up

    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
    Personendaten
    -0.76
     utafitiHapana
    -0.70
    Gön
    -0.69
    contentLoaded
    -0.68
     '\\;'
    -0.67
    enterOuterAlt
    -0.66
     autorytatywna
    -0.65
     Biôgrafia
    -0.63
     estekak
    -0.63
     Autorizaciones
    -0.61
    POSITIVE LOGITS
     géographique
    0.43
     destrucción
    0.43
     chewed
    0.43
     mangled
    0.41
     vieilles
    0.41
     mutilated
    0.41
     sepol
    0.40
     old
    0.39
     hiér
    0.38
     discusión
    0.38
    Activations Density 0.018%

    No Known Activations