© 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. 24-GEMMASCOPE-RES-16K
    6. 7329
    Prev
    Next
    INDEX
    Explanations

    names of individuals and their roles in community contexts

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

    Name followed by a verb of communication

    np_acts-logits-general · gemini-2.0-flash

    reporting speech and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hoea
    -0.52
    enschappe
    -0.47
    味が
    -0.46
    ControllerAdvice
    -0.46
    mybatisplus
    -0.45
    ftagPool
    -0.45
     failure
    -0.45
     plagio
    -0.44
     whilst
    -0.43
     unduly
    -0.43
    POSITIVE LOGITS
     says
    1.08
     credits
    1.05
     spiega
    0.95
     explicó
    0.92
     notes
    0.91
     explained
    0.91
     berättar
    0.91
     admits
    0.91
     forklar
    0.90
     explains
    0.90
    Activations Density 0.240%

    No Known Activations