© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 4083
    Prev
    Next
    INDEX
    Explanations

    terms related to stability and instability in various substances or conditions

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

    stable or unstable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     getField
    -0.42
     transfieras
    -0.41
     universal
    -0.40
     geno
    -0.40
    StoryboardSegue
    -0.38
     validamos
    -0.38
    begingroup
    -0.37
     pinulongan
    -0.37
     Universal
    -0.36
     scope
    -0.36
    POSITIVE LOGITS
     stabilizing
    0.89
     stabilize
    0.84
     stabilized
    0.84
     stabilization
    0.82
     instability
    0.82
     stability
    0.81
     Stabili
    0.79
     Instability
    0.79
     stabil
    0.78
     stabili
    0.78
    Activations Density 0.079%

    No Known Activations