© 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. 722
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming symbols along with related identifiers

    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
    principalTable
    -0.74
    )**
    -0.67
    ">//
    -0.65
    )$-
    -0.64
    RenderAtEndOf
    -0.61
    )}^{
    -0.61
    **********
    -0.58
    ****************
    -0.58
    intios
    -0.58
    **************
    -0.58
    POSITIVE LOGITS
    bateria
    0.57
    Према
    0.52
    ไง
    0.49
    asantry
    0.47
    clerview
    0.47
     Crypt
    0.45
     Sándor
    0.45
    ariConfig
    0.44
    ressum
    0.44
    IFORNIA
    0.43
    Activations Density 0.814%

    No Known Activations