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 - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 1
    Prev
    Next
    INDEX
    Explanations

    colloquial or informal language expressions, particularly in non-English languages.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @danielepoterti

    instances of repetition or variation in expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.40
    ęg
    -0.37
    calciatore
    -0.37
     Herausforderung
    -0.34
    rumah
    -0.32
    stattung
    -0.32
    ToRefresh
    -0.32
    ennom
    -0.31
    ität
    -0.31
    veröffentlichung
    -0.31
    POSITIVE LOGITS
     naman
    0.83
     же
    0.73
    MigrationBuilder
    0.69
    UnusedPrivate
    0.69
     zaś
    0.69
    OGND
    0.68
     lại
    0.65
     則
    0.61
     又
    0.61
     pedig
    0.61
    Activations Density 0.490%

    No Known Activations