© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 11709
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating possession or action in a context related to research or findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.76
    Portail
    -0.68
     AssemblyCulture
    -0.67
    στημα
    -0.65
     wrote
    -0.64
     knew
    -0.64
    EndInit
    -0.64
     Portail
    -0.62
    knew
    -0.60
    ]<<"
    -0.60
    POSITIVE LOGITS
     implications
    0.84
     ramifications
    0.71
     nothing
    0.70
     its
    0.68
     proven
    0.68
     never
    0.64
     resulted
    0.62
     betrekking
    0.61
     little
    0.61
     traditionally
    0.60
    Activations Density 0.231%

    No Known Activations