© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 4938
    Prev
    Next
    INDEX
    Explanations

    programming constructs, particularly related to data structures and HTTP client implementation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -1.20
    oredCriteria
    -0.94
     iprot
    -0.94
    AccessorTable
    -0.93
     мәкал
    -0.93
    StoryboardSegue
    -0.93
     disambiguazione
    -0.90
    تقاوى
    -0.89
     ComVisible
    -0.86
    DeleteBehavior
    -0.85
    POSITIVE LOGITS
     revanche
    0.45
     того
    0.42
     bestemt
    0.41
     possesso
    0.39
    hen
    0.39
     ég
    0.39
    dé
    0.39
    я
    0.39
    tilian
    0.38
    JsonPropertyName
    0.38
    Activations Density 0.070%

    No Known Activations