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-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16282
    Prev
    Next
    INDEX
    Explanations

    references to data structures or utility classes in programming

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

    Java `Arrays` class

    np_acts-logits-general · gemini-2.0-flash

    `java.util.Arrays` usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GetEnumerator
    -0.40
    RTCF
    -0.39
    setCell
    -0.38
     stanovnika
    -0.35
    tahankan
    -0.35
     pump
    -0.33
     בע
    -0.32
     dedans
    -0.32
     allocation
    -0.31
     perdita
    -0.31
    POSITIVE LOGITS
    stdc
    0.96
     Arrays
    0.68
    Arrays
    0.67
     فريبيس
    0.66
    AccessorTable
    0.60
    VIAF
    0.56
    ScopeManager
    0.53
    ConstraintMaker
    0.52
    SequentialGroup
    0.51
    Geographie
    0.50
    Activations Density 0.018%

    No Known Activations