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. 108670
    Prev
    Next
    INDEX
    Explanations

    words with the suffix 'ized' indicating a process of conversion or transformation

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

    words ending in -ize

    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
    LookAnd
    -0.62
     argc
    -0.55
    GHIJKLM
    -0.53
    pps
    -0.44
     المعيارى
    -0.43
     prochains
    -0.43
    ntlet
    -0.42
    ToReturn
    -0.41
    NSIndexPath
    -0.41
    adaptiveStyles
    -0.41
    POSITIVE LOGITS
    ized
    1.53
    IZED
    1.36
    izing
    1.35
    ization
    1.33
    ize
    1.33
    IZATION
    1.23
    izes
    1.20
    IZE
    1.18
    izable
    1.14
    IZING
    1.13
    Activations Density 0.096%

    No Known Activations