© 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. 8336
    Prev
    Next
    INDEX
    Explanations

    affirmative expressions and acknowledgments

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

    Affirmation or agreement ("OK", "Okay")

    np_acts-logits-general · gemini-2.0-flash

    agreement or acknowledgement

    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
     AssemblyCompany
    -0.54
     Administrativna
    -0.40
     varargin
    -0.37
    \{\\
    -0.33
     internetowa
    -0.33
    RetentionPolicy
    -0.33
     AttributeSet
    -0.33
    InitVars
    -0.33
    HostException
    -0.33
    ánicas
    -0.32
    POSITIVE LOGITS
     OK
    0.77
    Ok
    0.73
    OK
    0.71
     ok
    0.69
     Ok
    0.69
     okay
    0.66
     OKAY
    0.66
    addGap
    0.65
     Okay
    0.64
    isOk
    0.64
    Activations Density 0.056%

    No Known Activations