© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 2215
    Prev
    Next
    INDEX
    Explanations

    references to specific document sections and identifiers related to biological or medical sciences

    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
     <<<<<<<<<<<<<<
    -0.97
    تقاوى
    -0.78
    :✨
    -0.77
    \{\\
    -0.72
    сылкі
    -0.69
    +#+#
    -0.68
     سكانية
    -0.67
    +#+
    -0.66
    EndProject
    -0.64
    VersionUID
    -0.64
    POSITIVE LOGITS
    zzz
    0.73
    Cuz
    0.64
    s
    0.64
    zzzz
    0.63
     pz
    0.63
    zy
    0.61
     Nez
    0.60
    zie
    0.60
    Kuz
    0.60
    ZZZZ
    0.59
    Activations Density 0.145%

    No Known Activations