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. 11275
    Prev
    Next
    INDEX
    Explanations

    conversations and social interactions among individuals

    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
    __*/
    -0.48
    反应过来
    -0.46
    ">//
    -0.45
    Rè
    -0.44
    Weil
    -0.43
    igny
    -0.41
     utafitiHapana
    -0.41
    Попис
    -0.41
     BorderRadius
    -0.40
    MLLoader
    -0.40
    POSITIVE LOGITS
     talk
    3.29
     talking
    3.18
    talk
    2.95
     Talk
    2.89
     TALK
    2.79
    talking
    2.79
     talks
    2.77
     Talking
    2.77
    Talk
    2.77
     speak
    2.77
    Activations Density 0.664%

    No Known Activations