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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9-GEMMASCOPE-RES-16K
    6. 6616
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure, particularly in programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    MLLoader
    -0.65
    GEBURTSDATUM
    -0.62
    AnchorTagHelper
    -0.55
    المشاركات
    -0.54
    ソッド
    -0.53
    Geplaatst
    -0.52
    EndContext
    -0.52
    ImageContext
    -0.51
    tvguidetime
    -0.50
    脚注の使い方
    -0.50
    POSITIVE LOGITS
    lastIndexOf
    0.54
    indexOf
    0.50
    Contains
    0.47
    endswith
    0.46
     /\.
    0.45
     palabra
    0.45
    contains
    0.43
    IndexOf
    0.42
     obsah
    0.41
    toThrow
    0.40
    Activations Density 0.687%

    No Known Activations