© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 16208
    Prev
    Next
    INDEX
    Explanations

    events and conflicts in narratives

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

    a change or progression

    np_acts-logits-general · gemini-2.0-flash

    widens, thickens, or changes state

    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
    eckt
    -0.61
     supports
    -0.57
    ]--;
    -0.56
     OnTriggerEnter
    -0.56
     cares
    -0.55
    Гото
    -0.55
     Supports
    -0.55
     guarantees
    -0.55
     shares
    -0.54
    ngrx
    -0.53
    POSITIVE LOGITS
     wid
    0.79
     tight
    0.70
     deep
    0.70
     broad
    0.66
     becomes
    0.62
     thick
    0.62
     escal
    0.61
     shifts
    0.60
     shat
    0.59
     loos
    0.58
    Activations Density 0.540%

    No Known Activations