© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12105
    Prev
    Next
    INDEX
    Explanations

    concepts related to liberation and freedom from constraints

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

    freeing or escaping

    np_acts-logits-general · gemini-2.0-flash

    free from something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     ThemeData
    -0.45
    دانشنامهٔ
    -0.43
     estekak
    -0.43
     étoient
    -0.41
    toHaveBeenCalled
    -0.40
    ientôt
    -0.40
    Plural
    -0.40
     censiti
    -0.40
    hbs
    -0.39
    yarnpkg
    -0.38
    POSITIVE LOGITS
     escape
    0.81
     ESCAPE
    0.80
     extraction
    0.79
     liberation
    0.79
    脱
    0.76
     thoát
    0.75
     escaped
    0.74
     Extraction
    0.74
     escaping
    0.73
    ESCAPE
    0.73
    Activations Density 0.570%

    No Known Activations