© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 13377
    Prev
    Next
    INDEX
    Explanations

    references to age-specific demographics and related timeframes

    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
    存于互联网档案馆
    -0.78
     autorytatywna
    -0.68
    ⓧ
    -0.66
     Chwiliwch
    -0.64
     الحره
    -0.58
     المعرف
    -0.54
    __':
    -0.53
    __":
    -0.53
    RTGC
    -0.52
     "}";
    -0.51
    POSITIVE LOGITS
    WithMany
    0.56
    templateUrl
    0.53
    urlpatterns
    0.52
     anywhere
    0.51
     telefónica
    0.50
    ilares
    0.48
    AttributeSet
    0.48
     
    0.48
    onnaissance
    0.47
    PointerException
    0.45
    Activations Density 0.389%

    No Known Activations