© 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. 8392
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols

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

    Quotation marks followed by specific words

    np_acts-logits-general · gemini-2.0-flash

    citations and quotes

    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
    E
    -0.82
    S
    -0.81
    e
    -0.81
    P
    -0.80
    K
    -0.79
    WriteLiteral
    -0.79
    C
    -0.78
    l
    -0.77
    I
    -0.74
    X
    -0.72
    POSITIVE LOGITS
     myſelf
    1.46
     Theſe
    1.34
     Jefus
    1.29
     himſelf
    1.28
    ſelves
    1.27
     pleaſure
    1.26
     themſelves
    1.23
     uſed
    1.22
     whoſe
    1.21
     ainfi
    1.20
    Activations Density 1.653%

    No Known Activations