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. 14721
    Prev
    Next
    INDEX
    Explanations

    phrases that express totality or completeness

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

    Follows "completely" and describes an opinion

    np_acts-logits-general · gemini-2.0-flash

    completely + descriptive word

    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
     Slightly
    -0.73
     slightly
    -0.73
    slightly
    -0.71
     somewhat
    -0.70
    Slightly
    -0.69
    somewhat
    -0.66
     very
    -0.66
    AddHtmlAttribute
    -0.65
     agak
    -0.64
     really
    -0.63
    POSITIVE LOGITS
    IGraphics
    0.72
     utafitiHapana
    0.72
    tly
    0.59
    Composable
    0.59
    dientemente
    0.58
    летия
    0.58
     different
    0.57
     unrelated
    0.57
    不同
    0.56
     consultato
    0.56
    Activations Density 0.122%

    No Known Activations