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. 3-GEMMASCOPE-RES-16K
    6. 8859
    Prev
    Next
    INDEX
    Explanations

    references to offsets in data structure or programming context

    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
     vapore
    -0.72
    
    -0.71
    abestanden
    -0.69
    ActionCreators
    -0.68
     hvem
    -0.66
    lihatkan
    -0.66
     ruedas
    -0.65
     baterai
    -0.65
    FIG
    -0.65
    WritableDatabase
    -0.61
    POSITIVE LOGITS
     offset
    2.98
     Offset
    2.93
    offset
    2.73
     offsets
    2.71
    Offset
    2.63
     OFFSET
    2.33
    OFFSET
    2.25
    offsets
    1.97
    Offsets
    1.75
    偏移
    1.59
    Activations Density 0.122%

    No Known Activations