© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9845
    Prev
    Next
    INDEX
    Explanations

    formulations that indicate the presence of a statement or assertion

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

    "It" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    "it" sentence starter

    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
    ⤹
    -0.82
     houſe
    -0.66
     Italij
    -0.63
     myſelf
    -0.63
    makeConstraints
    -0.63
     pleaſure
    -0.62
     AssemblyCulture
    -0.61
    AISSEE
    -0.60
     queſta
    -0.60
    ArgsConstructor
    -0.60
    POSITIVE LOGITS
     fallu
    0.55
    makeText
    0.37
     finnas
    0.36
     habido
    0.35
    stdint
    0.32
     faut
    0.30
    
    0.29
     приходится
    0.29
    ]))
    0.29
     unlikely
    0.29
    Activations Density 0.288%

    No Known Activations