© 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. 5171
    Prev
    Next
    INDEX
    Explanations

    statistical factors and their significance in various contexts

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

    Follows punctuation (.,:) and "Among" or "including"

    np_acts-logits-general · gemini-2.0-flash

    among, including, one of

    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
    ьаж
    -0.46
     demais
    -0.35
    BackStack
    -0.34
    BaseAdapter
    -0.33
    jinal
    -0.31
    haltens
    -0.29
    ThroughAttribute
    -0.29
    redhat
    -0.29
    polazione
    -0.29
    ControllerTest
    -0.28
    POSITIVE LOGITS
     among
    1.20
    among
    1.18
     Among
    1.16
    Among
    1.11
     parmi
    1.03
     including
    1.02
    之一
    0.97
     antaranya
    0.97
    其中
    0.96
     amongst
    0.95
    Activations Density 0.600%

    No Known Activations