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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 21-GEMMASCOPE-RES-16K
    6. 14676
    Prev
    Next
    INDEX
    Explanations

    issues or challenges related to storage or management problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FormTagHelper
    -0.43
    ThroughAttribute
    -0.41
    webElement
    -0.37
    AVY
    -0.33
    anius
    -0.31
    に変
    -0.31
     intercamb
    -0.30
     vermelhas
    -0.30
    timedia
    -0.30
     fathoms
    -0.30
    POSITIVE LOGITS
     problem
    0.75
    problem
    0.75
     dilemma
    0.74
     PROBLEM
    0.72
    Problem
    0.72
     Problem
    0.71
    VersionUID
    0.69
     problème
    0.68
    problema
    0.68
    どうしよう
    0.67
    Activations Density 0.710%

    No Known Activations