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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 14006
    Prev
    Next
    INDEX
    Explanations

    references to edges in graphical representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    řízení
    -0.59
     âgées
    -0.56
     للمعارف
    -0.54
     judiciaire
    -0.53
    harusnya
    -0.53
     saucer
    -0.53
    ACTED
    -0.52
    SECT
    -0.52
     venganza
    -0.52
    });*/
    -0.52
    POSITIVE LOGITS
    AnchorStyles
    0.80
    帖最后由
    0.71
    EDEFAULT
    0.69
    sidemargin
    0.68
     EDGE
    0.66
     Мексичка
    0.66
    stones
    0.64
     edges
    0.64
     Edge
    0.62
    تقاوى
    0.62
    Activations Density 0.238%

    No Known Activations