Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 1116
    Prev
    Next
    INDEX
    Explanations

    adjectives indicating a high level of quality or status

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

    high followed by noun/adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    opsis
    -0.46
    PKG
    -0.46
     AssemblyProduct
    -0.45
    amante
    -0.44
    tpl
    -0.43
    ucle
    -0.42
    etta
    -0.42
     tablecloth
    -0.41
    aceae
    -0.41
    theless
    -0.40
    POSITIVE LOGITS
     High
    1.13
    High
    1.07
     HIGH
    0.99
     high
    0.95
    high
    0.92
    HIGH
    0.92
     Low
    0.72
    高
    0.70
    Low
    0.69
     高
    0.69
    Activations Density 0.079%

    No Known Activations