© 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. 12727
    Prev
    Next
    INDEX
    Explanations

    quotes or sayings that express wisdom regarding prevention and caution

    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
     المعيارى
    -0.76
    ticularly
    -0.63
    tamment
    -0.59
     للمعارف
    -0.58
     Pourtant
    -0.55
    StructEnd
    -0.54
    melten
    -0.54
    -------
    -0.53
    dibly
    -0.53
     Zwar
    -0.52
    POSITIVE LOGITS
    formKey
    0.57
    ViewChild
    0.57
    一分
    0.56
     adage
    0.56
     vaut
    0.55
     förr
    0.54
     opposites
    0.52
    lessed
    0.52
     يتيمه
    0.51
     Roskov
    0.51
    Activations Density 0.164%

    No Known Activations