© 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. 5-GEMMASCOPE-RES-16K
    11. 10880
    Prev
    Next
    INDEX
    Explanations

    phrases that express nuances in morality or legality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tư
    -0.53
     kaynağından
    -0.48
    []>
    -0.46
    NamedQuery
    -0.45
    횟
    -0.45
    toBeTruthy
    -0.45
    rrbracket
    -0.44
    tains
    -0.44
    ials
    -0.43
    bardier
    -0.43
    POSITIVE LOGITS
    tvguidetime
    0.75
     Roskov
    0.73
    AndEndTag
    0.71
     CreateTagHelper
    0.68
     dAtA
    0.63
    GEBURTSDATUM
    0.63
    évaluateur
    0.63
     समीक्षक
    0.62
    ropho
    0.60
    complexContent
    0.59
    Activations Density 0.321%

    No Known Activations