© 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. 12305
    Prev
    Next
    INDEX
    Explanations

    quote indicators or punctuation marks indicative of direct speech or citations

    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
    __':
    -0.66
     Baillargeon
    -0.63
    TabStop
    -0.62
     pe
    -0.58
    GenerationType
    -0.57
    ChildIndex
    -0.53
    letti
    -0.53
     grund
    -0.52
     picture
    -0.51
    XmlRootElement
    -0.51
    POSITIVE LOGITS
     myſelf
    0.78
     itſelf
    0.74
     himſelf
    0.73
     poffible
    0.72
     ſche
    0.70
     themſelves
    0.68
     ſever
    0.67
     diſt
    0.67
     Jefus
    0.66
     fubject
    0.65
    Activations Density 0.040%

    No Known Activations