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. 24-GEMMASCOPE-RES-16K
    6. 4316
    Prev
    Next
    INDEX
    Explanations

    interactions between animals and their environment, particularly focusing on dogs and their behaviors

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

    motion or movement

    np_acts-logits-general · gemini-2.0-flash

    words describing fast movement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     endblock
    -0.73
     ainfi
    -0.66
     Grecs
    -0.63
    setVerticalGroup
    -0.60
     auffi
    -0.58
     vernie
    -0.57
     houſe
    -0.57
     raiſ
    -0.55
     avoit
    -0.55
    Instantiate
    -0.54
    POSITIVE LOGITS
     whi
    0.89
     dart
    0.83
     racing
    0.82
     care
    0.82
     chug
    0.82
     sau
    0.81
     zooming
    0.81
     scur
    0.81
     flit
    0.81
     zi
    0.80
    Activations Density 0.304%

    No Known Activations