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. 7-GEMMASCOPE-RES-16K
    6. 4629
    Prev
    Next
    INDEX
    Explanations

    references to mobile or movable equipment and vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sky
    -0.44
    Peak
    -0.39
     peaked
    -0.39
     foly
    -0.38
    CLC
    -0.38
     peak
    -0.38
    垣
    -0.37
     Peak
    -0.36
    쌓
    -0.36
    peak
    -0.36
    POSITIVE LOGITS
     Movers
    1.14
     moved
    1.13
    Moved
    1.10
     Moved
    1.09
     moving
    1.09
     movers
    1.09
     Moving
    1.08
    moved
    1.08
     moves
    1.08
     Moves
    1.07
    Activations Density 0.488%

    No Known Activations