© 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. 8329
    Prev
    Next
    INDEX
    Explanations

    personal reflections and statements of belief

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

    "I" followed by a verb expressing an opinion

    np_acts-logits-general · gemini-2.0-flash

    personal beliefs or opinions

    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
    RenderAtEndOf
    -0.95
    IsMutable
    -0.80
     समीक्षाओं
    -0.78
     rhestr
    -0.76
    /**
    -0.75
    thâu
    -0.73
     وتسجيلات
    -0.73
     فريبيس
    -0.71
    PasswordEncoder
    -0.71
    CloseOperation
    -0.70
    POSITIVE LOGITS
     personally
    0.69
     contoh
    0.62
    Personal
    0.54
     persönlich
    0.53
     personalmente
    0.53
     personlig
    0.53
     witnessed
    0.52
     Personal
    0.52
     itse
    0.52
     personal
    0.51
    Activations Density 0.318%

    No Known Activations