© 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-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 13273
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "move" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cyfarwyddwr
    -0.49
    cshtml
    -0.47
     returning
    -0.45
    Tembelea
    -0.44
     turning
    -0.44
    RuntimeObject
    -0.43
     незавершена
    -0.42
    nationality
    -0.41
     machinery
    -0.40
     Wheat
    -0.39
    POSITIVE LOGITS
    Move
    1.27
     move
    1.23
    move
    1.20
     Move
    1.20
     moves
    1.09
     Moves
    1.02
    moves
    1.02
     MOVE
    0.99
    Moves
    0.98
    MOVE
    0.93
    Activations Density 0.106%

    No Known Activations