© 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. 31-GEMMASCOPE-RES-16K
    11. 11787
    Prev
    Next
    INDEX
    Explanations

    details related to hostage situations and legal conditions

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

    words that describe the release or freeing of people from captivity or detention.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ISTRATION
    -0.48
     समीक्षाओं
    -0.43
    gios
    -0.42
     jScrollPane
    -0.42
     chev
    -0.41
     мәкал
    -0.41
    neté
    -0.41
    ItemBackground
    -0.41
    postsleuth
    -0.41
    TestingModule
    -0.41
    POSITIVE LOGITS
     release
    1.88
     released
    1.70
     freed
    1.68
    Release
    1.68
    release
    1.68
     Release
    1.66
     freeing
    1.63
     liberation
    1.58
     freedom
    1.56
     liberación
    1.54
    Activations Density 0.613%

    No Known Activations