© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 547
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases suggesting comparisons or conditions within a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the conjunction "and" used to connect clauses or list items in formal technical writing.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     мәкал
    -0.56
    rungsseite
    -0.54
     ")[
    -0.48
    باط
    -0.47
    Билгалдахарш
    -0.47
     propOrder
    -0.45
    mybatisplus
    -0.45
     bỏ
    -0.45
    }}}
    -0.45
     mắc
    -0.45
    POSITIVE LOGITS
     of
    0.45
     else
    0.42
    UrlResolution
    0.40
     hence
    0.40
     AppCompatTheme
    0.39
     consequently
    0.38
     terhadap
    0.38
    Tentang
    0.37
     zejména
    0.36
    zarchiwizowane
    0.36
    Activations Density 1.183%

    No Known Activations