© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 13092
    Prev
    Next
    INDEX
    Explanations

    occurrences of underscore-prefixed identifiers, commonly used in programming, especially in code related to libraries or frameworks

    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
     itſelf
    -1.12
     ་་
    -0.97
     faſt
    -0.84
     ―――――
    -0.84
     foon
    -0.83
     myſelf
    -0.83
     raiſ
    -0.82
     Jefus
    -0.79
     doubtnut
    -0.79
     Majefty
    -0.79
    POSITIVE LOGITS
     _
    2.82
    (_
    1.82
    ._
    1.81
     (_
    1.74
    =_
    1.69
    ,_
    1.65
    :_
    1.60
     *_
    1.60
     !_
    1.52
    ::_
    1.51
    Activations Density 0.102%

    No Known Activations