© 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. 18-GEMMASCOPE-RES-16K
    11. 6829
    Prev
    Next
    INDEX
    Explanations

    negative phrases and variations of lack or absence

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

    Expressing a cessation or discontinuation

    np_acts-logits-general · gemini-2.0-flash

    no longer/anymore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.75
    DockStyle
    -0.72
    AnchorStyles
    -0.66
     JpaRepository
    -0.65
    principalColumn
    -0.65
    Hentet
    -0.65
     HasFactory
    -0.61
     createContext
    -0.61
    gonic
    -0.59
     متعلقه
    -0.58
    POSITIVE LOGITS
     anymore
    2.67
     enää
    1.58
     now
    1.45
     lagi
    1.41
     artık
    1.31
    了
    1.24
     теперь
    1.21
    now
    1.18
     désormais
    1.18
     ormai
    1.14
    Activations Density 0.283%

    No Known Activations