© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 11850
    Prev
    Next
    INDEX
    Explanations

    formatting cues and timestamps in text

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

    Negative statements including "I don't"

    np_acts-logits-general · gemini-2.0-flash

    opinion or statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.69
     desmotivaciones
    -0.67
    LookAnd
    -0.66
    parsedMessage
    -0.65
    windowFixed
    -0.63
     surla
    -0.61
    WriteLiteral
    -0.60
     CreateTagHelper
    -0.59
    nodoc
    -0.58
    ſelves
    -0.58
    POSITIVE LOGITS
    inaudible
    0.39
     podcast
    0.37
    
    0.36
     Podcast
    0.35
     Approval
    0.35
     confor
    0.33
     voll
    0.32
    킵
    0.32
    ACY
    0.31
     Differential
    0.31
    Activations Density 0.077%

    No Known Activations