© 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. 7-GEMMASCOPE-RES-16K
    11. 14527
    Prev
    Next
    INDEX
    Explanations

    patterns in legal or formal document structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -1.09
     createSlice
    -0.93
    Personensuche
    -0.93
     Borja
    -0.92
    LookAnd
    -0.87
    NameInMap
    -0.85
    WithIOException
    -0.85
    évaluateur
    -0.82
     Fod
    -0.81
    awtextra
    -0.81
    POSITIVE LOGITS
    ________________
    1.84
    _______
    1.16
    _____
    1.16
    ______________
    1.15
    ____
    1.15
    ______
    1.14
    _____________
    1.03
    ____________
    1.01
    _______________
    1.01
     ____________
    1.01
    Activations Density 0.072%

    No Known Activations