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. 2355
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional states and interpersonal dynamics

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

    before infinitives ("to," "must," etc.)

    np_acts-logits-general · gemini-2.0-flash

    cessation or continuation

    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
    csolódó
    -0.59
    intenant
    -0.57
     Throwable
    -0.56
    existsSync
    -0.56
    "?>
    -0.56
     بدان
    -0.55
    consider
    -0.54
     ufe
    -0.52
     используют
    -0.51
    Use
    -0.50
    POSITIVE LOGITS
     fall
    1.06
     fade
    0.91
     rise
    0.88
     end
    0.87
     disappear
    0.86
     drop
    0.83
     evaporate
    0.82
     pop
    0.81
     vanish
    0.79
     turn
    0.79
    Activations Density 0.818%

    No Known Activations