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. 12654
    Prev
    Next
    INDEX
    Explanations

    references to movement or directional cues

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

    Directional movement: up or down

    np_acts-logits-general · gemini-2.0-flash

    direction and 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
     AssemblyCulture
    -0.81
    kháu
    -0.66
    Down
    -0.57
    DOWN
    -0.56
     AssemblyCompany
    -0.55
     downward
    -0.52
    Personensuche
    -0.52
    down
    -0.51
    ніципа
    -0.51
    ไตล์
    -0.51
    POSITIVE LOGITS
     into
    0.68
     past
    0.67
    river
    0.63
     onto
    0.62
    wind
    0.59
    past
    0.58
     towards
    0.57
    devtools
    0.56
     toward
    0.56
    LayoutPanel
    0.55
    Activations Density 0.096%

    No Known Activations