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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 23-GEMMASCOPE-RES-16K
    6. 11237
    Prev
    Next
    INDEX
    Explanations

    references to legal frameworks and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -0.68
     الحره
    -0.64
    ivable
    -0.61
    webElementXpaths
    -0.59
    rayage
    -0.56
    lė
    -0.56
    esez
    -0.54
     žaid
    -0.54
    phrag
    -0.51
    haustible
    -0.51
    POSITIVE LOGITS
     criminal
    1.34
     crime
    1.33
    criminal
    1.15
    crime
    1.15
     Criminal
    1.14
     Crime
    1.12
     crimin
    1.12
    Criminal
    1.09
    Crime
    1.09
     CRIMINAL
    1.04
    Activations Density 0.737%

    No Known Activations