© 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. 8368
    Prev
    Next
    INDEX
    Explanations

    references to firearm types, specifically shotguns and their features

    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
     zoll
    -0.59
    Diweddarwch
    -0.56
     незавершена
    -0.54
    +#+
    -0.53
     autorytatywna
    -0.52
    AnchorStyles
    -0.50
     McCar
    -0.50
     Normdatei
    -0.49
    atzung
    -0.49
     للاسماء
    -0.49
    POSITIVE LOGITS
     Airs
    0.68
     pellets
    0.67
     pellet
    0.64
     Cros
    0.64
     paintball
    0.62
     BB
    0.61
     airsoft
    0.61
    Cros
    0.60
    pel
    0.59
     bb
    0.58
    Activations Density 0.297%

    No Known Activations