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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 69360
    Prev
    Next
    INDEX
    Explanations

    the name "Grissom" and variations of the name "Pr"

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

    Grissom and words starting with Pr

    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
     nahilalakip
    -0.59
    toJSONString
    -0.58
     Hanover
    -0.56
    لينكات
    -0.55
    Hozzáférés
    -0.53
     Pellegrini
    -0.52
    SequentialGroup
    -0.52
     Weiner
    -0.52
     Pavia
    -0.51
     Selected
    -0.50
    POSITIVE LOGITS
     Pr
    0.75
     Pl
    0.71
     Gr
    0.71
     Br
    0.71
    Pr
    0.70
     Bl
    0.68
     Fr
    0.64
     Kl
    0.64
     Gl
    0.63
     Sm
    0.63
    Activations Density 0.022%

    No Known Activations