© 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. 881
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and programming syntax

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

    Follows a hyphen

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation symbols

    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
     Theſe
    -1.30
     myſelf
    -1.29
     itſelf
    -1.21
     betweenstory
    -1.17
     Мексичка
    -1.15
     Monfieur
    -1.12
     ExecuteAsync
    -1.08
     himſelf
    -1.06
     Efq
    -1.05
    ^(@)
    -1.02
    POSITIVE LOGITS
    <eos>
    0.59
    err
    0.54
    <unused61>
    0.54
    <unused62>
    0.53
    <unused63>
    0.52
     Ho
    0.50
    erv
    0.49
     pres
    0.48
    ir
    0.48
    ni
    0.48
    Activations Density 0.558%

    No Known Activations