© 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. 2976
    Prev
    Next
    INDEX
    Explanations

    references to authority and statements about legality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    terms related to legal authority and regulations regarding events

    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
    OrNil
    -0.68
     Walkover
    -0.61
     doInBackground
    -0.58
    chriften
    -0.58
    FormState
    -0.56
    WebElementEntity
    -0.56
    findpost
    -0.55
     iArr
    -0.55
    🏻‍♀️
    -0.54
     gouver
    -0.54
    POSITIVE LOGITS
     hence
    0.79
     especially
    0.74
    hence
    0.65
     المعيارى
    0.63
     particularly
    0.61
    especially
    0.60
     preparatory
    0.58
     judging
    0.58
     thereby
    0.58
     coupled
    0.57
    Activations Density 0.095%

    No Known Activations