© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4217
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to data structures and their properties

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

    Preceding protein or gene identifiers

    np_acts-logits-general · gemini-2.0-flash

    NP IP RP HSP disrup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <h2>
    -0.40
    er
    -0.34
    /**
    -0.33
    are
    -0.33
    RTDA
    -0.31
     zaak
    -0.30
    elerik
    -0.30
    "
    -0.30
    ع
    -0.30
    ைய
    -0.29
    POSITIVE LOGITS
    pable
    0.72
    CloseOperation
    0.68
    Tē
    0.66
     yp
    0.64
    nop
    0.64
     tp
    0.63
     YP
    0.62
     Audiodateien
    0.61
     Nop
    0.60
     Kip
    0.60
    Activations Density 2.858%

    No Known Activations