© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8791
    Prev
    Next
    INDEX
    Explanations

    mentions of significant awards or honors

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

    Title or position of a political figure

    np_acts-logits-general · gemini-2.0-flash

    former political titles

    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
    PLICATIONS
    -0.37
    ListModule
    -0.35
     wst
    -0.35
     hulle
    -0.34
    NextPage
    -0.33
    folgung
    -0.33
    ]=="
    -0.33
    
    -0.33
     quæ
    -0.33
     Embora
    -0.32
    POSITIVE LOGITS
     President
    1.51
    President
    1.34
     Governor
    1.34
     president
    1.21
    Governor
    1.17
     governor
    1.13
     PRESIDENT
    1.12
     Mayor
    1.10
    president
    1.07
     Minister
    1.06
    Activations Density 0.752%

    No Known Activations