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. 21-GEMMASCOPE-RES-16K
    6. 7459
    Prev
    Next
    INDEX
    Explanations

    code syntax elements related to functions and variables in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    -0.99
    </strong>
    -0.80
    TagMode
    -0.60
    цездатний
    -0.59
    })$}
    -0.58
     oprot
    -0.57
     }}$}
    -0.55
    saraba
    -0.54
     دیکھیے
    -0.52
    </em>
    -0.51
    POSITIVE LOGITS
    <eos>
    1.44
    ↵↵
    1.22
    ↵↵↵
    1.11
    ↵↵↵↵
    1.11
    ↵↵↵↵↵
    1.10
    ↵↵↵↵↵↵
    1.07
    ↵↵↵↵↵↵↵↵
    1.06
    ↵↵↵↵↵↵↵
    1.02
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.97
    ↵↵↵↵↵↵↵↵↵
    0.95
    Activations Density 0.243%

    No Known Activations