© 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. 1646
    Prev
    Next
    INDEX
    Explanations

    references to legal arguments and concepts related to court cases

    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
     myſelf
    -0.69
     himſelf
    -0.65
     itſelf
    -0.61
     femininos
    -0.58
     quæ
    -0.57
     Efq
    -0.56
     Theſe
    -0.55
     BoxDecoration
    -0.52
    <bos>
    -0.52
     Eſ
    -0.51
    POSITIVE LOGITS
     claim
    1.57
     claims
    1.36
     argue
    1.36
     assert
    1.29
     contends
    1.25
    claim
    1.24
     contend
    1.24
     claimed
    1.23
     argued
    1.22
     claiming
    1.20
    Activations Density 0.893%

    No Known Activations