© 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. 23-GEMMASCOPE-RES-16K
    11. 8804
    Prev
    Next
    INDEX
    Explanations

    references to individuals or groups and their relationships within a societal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itself
    -0.64
    eseorang
    -0.62
     ninguém
    -0.61
     anyone
    -0.61
     individuals
    -0.60
    nobody
    -0.59
     seseorang
    -0.59
     itſelf
    -0.59
     anybody
    -0.59
    anyone
    -0.59
    POSITIVE LOGITS
     whom
    1.32
    whom
    1.06
     whose
    0.78
     who
    0.76
    whose
    0.71
    ترم
    0.69
    Whose
    0.67
    Whom
    0.66
    تفصیلات
    0.63
     sexe
    0.63
    Activations Density 0.528%

    No Known Activations