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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 17-GEMMASCOPE-RES-16K
    6. 13549
    Prev
    Next
    INDEX
    Explanations

    semicolon and null references in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    
    -0.83
    __':
    -0.76
    MergeFrom
    -0.68
    featureID
    -0.61
     Gilli
    -0.61
    NewUrlParser
    -0.58
    IVEREF
    -0.57
    igera
    -0.56
     وتسجيلات
    -0.56
    writerow
    -0.55
    POSITIVE LOGITS
    expandindo
    0.75
    makeConstraints
    0.60
     pronti
    0.56
     próprios
    0.53
     žád
    0.52
     förb
    0.49
     nargin
    0.48
     Vandal
    0.46
     Bettina
    0.46
     protoimpl
    0.46
    Activations Density 0.060%

    No Known Activations