© 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. 6-GEMMASCOPE-RES-16K
    11. 5551
    Prev
    Next
    INDEX
    Explanations

    structured or numeric patterns in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    saraba
    -0.65
    はじめに
    -0.64
    uitton
    -0.60
    ellemző
    -0.59
    Scénario
    -0.59
    SPATH
    -0.57
    Handlung
    -0.56
    müş
    -0.55
    rophoresis
    -0.55
    στό
    -0.55
    POSITIVE LOGITS
    XmlEnum
    0.55
    èdia
    0.54
    انيف
    0.52
    numerusform
    0.52
    RetentionPolicy
    0.51
     OMITBAD
    0.51
     Normdatei
    0.50
    endpush
    0.50
    usercontent
    0.50
    OptionsMenu
    0.48
    Activations Density 0.875%

    No Known Activations