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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 1065
    Prev
    Next
    INDEX
    Explanations

    database-related terminology and structure references

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

    database query and code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndGlobalSection
    -0.73
     Infórmanos
    -0.66
    IUrlHelper
    -0.65
    AndroidJUnit
    -0.61
     HasFactory
    -0.59
    ChildScrollView
    -0.58
    rungsseite
    -0.56
    Personensuche
    -0.55
    LookAnd
    -0.54
     AppCompatTheme
    -0.54
    POSITIVE LOGITS
    imetry
    0.33
     Pud
    0.33
     minority
    0.32
     उद
    0.31
    Pud
    0.31
     stel
    0.30
     ref
    0.29
    AutoSize
    0.29
     heating
    0.29
    resave
    0.29
    Activations Density 0.001%

    No Known Activations