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-2-2B
    4. Residual Stream - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1815
    Prev
    Next
    INDEX
    Explanations

    text related to blog subscriptions and affiliate marketing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.63
    migrationBuilder
    -0.63
     виправивши
    -0.60
     <<<<<<<<<<<<<<
    -0.60
     Exactos
    -0.58
     pinulongan
    -0.56
    setViewName
    -0.56
    __(/*!
    -0.55
    arton
    -0.54
     AssemblyProduct
    -0.54
    POSITIVE LOGITS
    StoryboardSegue
    0.58
    MethodManager
    0.54
     Amazon
    0.50
     vendita
    0.48
    braio
    0.48
    ماية
    0.48
    multicolumn
    0.48
    ╚
    0.48
     Amy
    0.47
    persky
    0.45
    Activations Density 0.020%

    No Known Activations