© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 1139
    Prev
    Next
    INDEX
    Explanations

    intense physical sensations and descriptions of characters' states or appearances

    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
    :✨
    -0.75
     Namely
    -0.62
     Basically
    -0.59
     basically
    -0.57
    Basically
    -0.57
     defStyle
    -0.55
    namely
    -0.55
     befindet
    -0.54
     handelt
    -0.53
     ladite
    -0.53
    POSITIVE LOGITS
    Tikang
    0.64
     läßt
    0.60
    emptory
    0.54
     implacable
    0.53
     Apalagi
    0.53
    Демографія
    0.52
     straining
    0.52
    dafx
    0.52
    identiality
    0.50
     hurrying
    0.50
    Activations Density 0.378%

    No Known Activations