© 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 106010
    Prev
    Next
    INDEX
    Explanations

    commands related to creating and manipulating data structures or records

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    windowFixed
    -0.69
     ujednoznacz
    -0.60
    StoryboardSegue
    -0.58
    GEBURTS
    -0.56
    Bakgrunnsstoff
    -0.53
     Réponses
    -0.51
    parsedMessage
    -0.51
     OMITBAD
    -0.49
    msgSender
    -0.47
    Референце
    -0.47
    POSITIVE LOGITS
     guste
    0.41
     ti
    0.38
    askar
    0.38
    DIPSETTING
    0.36
    frost
    0.36
    Abit
    0.36
    其
    0.36
     partial
    0.36
     ts
    0.35
     Te
    0.35
    Activations Density 0.060%

    No Known Activations