© 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. 9-GEMMASCOPE-RES-16K
    11. 11470
    Prev
    Next
    INDEX
    Explanations

    themes of conflict and struggle against evil forces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AutoScaleMode
    -0.54
     ब्रेकडाउन
    -0.48
    endcsname
    -0.47
    InjectAttribute
    -0.43
    enderror
    -0.43
     fieldNum
    -0.41
    ViewInit
    -0.41
     aDecoder
    -0.40
    withIdentifier
    -0.40
    PropertyChanging
    -0.38
    POSITIVE LOGITS
     invading
    0.53
     invaders
    0.51
     ISIS
    0.49
     Invasive
    0.46
    TagMode
    0.45
     invasive
    0.45
     Enemy
    0.44
    arrings
    0.44
     attackers
    0.42
    Enemy
    0.41
    Activations Density 1.385%

    No Known Activations