© 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. 8-GEMMASCOPE-RES-16K
    11. 3422
    Prev
    Next
    INDEX
    Explanations

    sections with structured text or mathematical formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.79
    <eos>
    -0.71
    /
    -0.67
    ’
    -0.64
    '
    -0.63
    </em>
    -0.59
     '
    -0.56
    mathrm
    -0.55
     and
    -0.54
    2
    -0.53
    POSITIVE LOGITS
    setVerticalGroup
    1.45
     propOrder
    1.33
     ModelExpression
    1.28
    GEBURTSDATUM
    1.23
     '\\;'
    1.22
     AssemblyCulture
    1.20
     CreateTagHelper
    1.19
     незавершена
    1.18
     Audiodateien
    1.16
    styleType
    1.16
    Activations Density 4.530%

    No Known Activations