© 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. 11055
    Prev
    Next
    INDEX
    Explanations

    references to the concept of identity and its implications, particularly in legal contexts

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

    Pronoun immediately after brackets

    np_acts-logits-general · gemini-2.0-flash

    pronouns and identifiers

    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
     CreateTagHelper
    -1.12
    ChildScrollView
    -0.79
    ViewFeatures
    -0.73
     '\\;'
    -0.71
     дописавши
    -0.70
    EndInit
    -0.70
    aarrggbb
    -0.67
     виправивши
    -0.64
    SequentialGroup
    -0.63
    Véxase
    -0.62
    POSITIVE LOGITS
    中略
    1.04
    sic
    0.90
     uſ
    0.68
    })`
    0.67
     beſt
    0.67
     itſelf
    0.67
     Añade
    0.67
    ſelf
    0.66
     pleaſure
    0.65
     reaſon
    0.65
    Activations Density 0.148%

    No Known Activations