© 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. 258
    Prev
    Next
    INDEX
    Explanations

    expressions of personal opinions and reflective thoughts

    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
    PreferredItem
    -0.67
     legit
    -0.65
    دانشنامهٔ
    -0.64
     lenker
    -0.60
    ItemBackground
    -0.59
     TextAppearance
    -0.58
     HttpNotFound
    -0.57
    extAlignment
    -0.57
    transQ
    -0.56
    bosis
    -0.56
    POSITIVE LOGITS
     supposes
    0.60
     suppose
    0.59
    بدو
    0.59
     skall
    0.56
     Audiodateien
    0.51
    stdarg
    0.51
     confess
    0.51
     Waray
    0.51
     wonder
    0.50
    จัก
    0.50
    Activations Density 0.328%

    No Known Activations