© 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. 8620
    Prev
    Next
    INDEX
    Explanations

    content related to various forms of media and evidence presentation in reporting

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

    after "especially" or "except"

    np_acts-logits-general · gemini-2.0-flash

    content types and discourse modifiers

    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
    principalColumn
    -0.38
     drove
    -0.35
    WithIOException
    -0.35
    atisk
    -0.34
    pgterms
    -0.34
    XmlIgnore
    -0.32
     Sever
    -0.32
    SharedDtor
    -0.31
     mali
    -0.30
     Quiet
    -0.30
    POSITIVE LOGITS
     biographies
    0.63
     textual
    0.63
     pictorial
    0.62
    ApiModelProperty
    0.60
     storytelling
    0.60
     autobio
    0.59
     audiobooks
    0.59
     narration
    0.58
     narrative
    0.57
     descriptive
    0.57
    Activations Density 1.080%

    No Known Activations