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. 12639
    Prev
    Next
    INDEX
    Explanations

    expressions related to perception and evaluation of experiences

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

    Preceding verbs/adjectives implying appearance

    np_acts-logits-general · gemini-2.0-flash

    looks like

    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
     Kinds
    -0.85
    LIKE
    -0.77
    Like
    -0.75
     Types
    -0.74
    Similar
    -0.73
     Like
    -0.73
    unlike
    -0.72
    kinds
    -0.72
    Unlike
    -0.67
    Kinds
    -0.66
    POSITIVE LOGITS
    الحياه
    0.59
     li
    0.56
    تقاوى
    0.55
     lenker
    0.54
     lie
    0.53
    Visitor
    0.52
    fjspx
    0.52
    igue
    0.50
    LIE
    0.49
    Gambas
    0.49
    Activations Density 0.119%

    No Known Activations