© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8213
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation in the text

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

    Code, especially semicolons and brackets

    np_acts-logits-general · gemini-2.0-flash

    code structures

    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
     GenerationType
    -0.62
     Autorizaciones
    -0.58
     arşivlendi
    -0.54
    קישורים
    -0.52
     transférez
    -0.50
    ädie
    -0.50
     ModelExpression
    -0.49
    Uninitialized
    -0.48
    Попис
    -0.48
     PUBLICATION
    -0.47
    POSITIVE LOGITS
    paksa
    0.63
     Knob
    0.63
    Bennett
    0.63
    DebuggerStep
    0.62
     circunstan
    0.62
    UnknownFields
    0.61
     Namur
    0.60
     Esperanza
    0.59
     Limoges
    0.59
     ordres
    0.59
    Activations Density 0.176%

    No Known Activations