© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 9978
    Prev
    Next
    INDEX
    Explanations

    concepts related to stability and instability in various contexts

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

    Talks about stability and instability

    np_acts-logits-general · gemini-2.0-flash

    stability, stable, instability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    참고
    -0.42
     Grou
    -0.42
     MainAxisSize
    -0.40
    Gong
    -0.38
     بتاريخ
    -0.37
     viewType
    -0.37
    urgy
    -0.36
     căr
    -0.35
    SPJ
    -0.35
     CURIAM
    -0.35
    POSITIVE LOGITS
     stability
    1.75
     instability
    1.59
     Stability
    1.58
    Stability
    1.58
     unstable
    1.56
    stability
    1.56
    Stable
    1.53
     stable
    1.52
     Stable
    1.51
     stabili
    1.48
    Activations Density 0.208%

    No Known Activations