Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 8504
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "shoot" and its variants in different contexts

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

    the word "shoot"

    np_acts-logits-general · gemini-2.0-flash

    shoot to fame or firing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Numerade
    -0.75
    ]--;
    -0.64
    mặt
    -0.61
    extAlignment
    -0.61
    defineProperty
    -0.59
    "}"
    -0.58
    imum
    -0.58
     Interchange
    -0.57
    WebControls
    -0.57
    eably
    -0.56
    POSITIVE LOGITS
     shooting
    1.03
     shot
    1.02
     shoots
    0.98
     shots
    0.94
     shoot
    0.92
    shot
    0.92
     Shooting
    0.90
     Shot
    0.87
     SHOT
    0.84
    Shot
    0.84
    Activations Density 0.259%

    No Known Activations