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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 16173
    Prev
    Next
    INDEX
    Explanations

    closing brackets and semicolons in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.75
    alyptus
    -0.67
     dAtA
    -0.60
    󠁴
    -0.60
    ględ
    -0.59
     оригіналу
    -0.59
    lgari
    -0.57
    oredCriteria
    -0.57
    ApiModelProperty
    -0.57
    FunctionFlags
    -0.56
    POSITIVE LOGITS
    __':
    0.67
    ↵↵
    0.67
     otomatig
    0.65
    <eos>
    0.60
    localctx
    0.59
    __':
    
    0.59
    ]--;
    0.56
    __":
    
    0.56
    CodeAnalysis
    0.55
    EndGlobalSection
    0.55
    Activations Density 0.091%

    No Known Activations