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-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8305
    Prev
    Next
    INDEX
    Explanations

    indents or whitespace in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.66
     Anſ
    -0.66
     againſt
    -0.64
     Efq
    -0.62
     itſelf
    -0.61
     raiſ
    -0.59
     Majefty
    -0.59
     ſtate
    -0.59
     macros
    -0.58
     Shaksp
    -0.57
    POSITIVE LOGITS
    __':
    
    0.69
    migrationBuilder
    0.68
    Портал
    0.65
    __);
    0.65
    --;
    0.63
    __':
    0.57
    titleMargin
    0.57
     IBOutlet
    0.56
    >>();
    0.56
    ImageContext
    0.56
    Activations Density 0.243%

    No Known Activations