© 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. 25-GEMMASCOPE-RES-16K
    11. 1120
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and structure, particularly involving vectors and data types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DIPSETTING
    -0.61
    RenderAtEndOf
    -0.59
     onOptions
    -0.54
    FontOfSize
    -0.52
    はじめに
    -0.51
    VIAF
    -0.51
    críbete
    -0.49
    )++;
    -0.49
     whoever
    -0.48
     NUKAT
    -0.47
    POSITIVE LOGITS
     listOf
    0.83
     allowed
    0.70
     arrayOf
    0.70
    allowed
    0.69
     lst
    0.69
    NameList
    0.65
     Allowed
    0.65
    listOf
    0.65
     arr
    0.64
    all
    0.63
    Activations Density 0.280%

    No Known Activations