© 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. 14911
    Prev
    Next
    INDEX
    Explanations

    indications of assessment or evaluation

    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
    туа
    -0.48
     ideas
    -0.46
    kháu
    -0.45
     sogen
    -0.45
    asian
    -0.44
    noindent
    -0.44
    params
    -0.44
     updateTime
    -0.43
     أجل
    -0.43
    defineProperty
    -0.42
    POSITIVE LOGITS
     judging
    1.26
     based
    1.22
    Judging
    1.17
     anhand
    1.16
     Based
    1.12
     Judging
    1.11
     BASED
    1.07
    Based
    1.03
     berdasarkan
    1.00
     looking
    0.98
    Activations Density 0.434%

    No Known Activations