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 - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 896
    Prev
    Next
    INDEX
    Explanations

    code or variables related to data processing and transfers, especially involving byte lengths and expected versus received values

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

    target temperature or goal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    
    -0.59
     Wiktionnaire
    -0.51
    __":
    
    -0.51
    ThroughAttribute
    -0.50
    __':
    -0.49
    _<
    -0.48
     dieſem
    -0.48
    ंदीखरीदारी
    -0.48
    ++
    
    -0.47
     quæ
    -0.47
    POSITIVE LOGITS
    tagPool
    0.41
    currentTarget
    0.38
     full
    0.37
     total
    0.36
    jsonwebtoken
    0.35
     oorspron
    0.34
     penuh
    0.34
    full
    0.33
     mål
    0.33
     goal
    0.33
    Activations Density 0.028%

    No Known Activations