© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8426
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and constitutional concepts

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

    doubt or uncertainty

    np_acts-logits-general · gemini-2.0-flash

    doubt and questioning

    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
    Obrázky
    -0.34
     spin
    -0.34
    TagHelper
    -0.32
    ्त
    -0.30
     fon
    -0.29
     feature
    -0.29
     Wing
    -0.29
     ویکی
    -0.29
    IntOverflow
    -0.29
     attra
    -0.29
    POSITIVE LOGITS
     doubtful
    1.56
     questionable
    1.55
     doubted
    1.45
     dubious
    1.42
     doubts
    1.41
     doubt
    1.31
     doubting
    1.28
     cuestion
    1.27
     doute
    1.27
    doubt
    1.25
    Activations Density 0.546%

    No Known Activations