© 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. 31-GEMMASCOPE-RES-16K
    11. 5599
    Prev
    Next
    INDEX
    Explanations

    references to freshness or newness in various contexts

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

    the word "fresh" appearing at the beginning of phrases or titles.

    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
    oa̍t
    -0.52
    Життєпис
    -0.50
     صوتيه
    -0.47
    UserDao
    -0.42
    FirebaseAuth
    -0.41
    Билгалдахарш
    -0.40
     يتيمه
    -0.39
    IInterface
    -0.39
     isNameExpr
    -0.39
    метров
    -0.37
    POSITIVE LOGITS
    Fresh
    1.03
     Fresh
    0.99
     FRESH
    0.96
    fresh
    0.94
     fresh
    0.92
    FRESH
    0.86
     freshness
    0.83
     fresca
    0.77
     frescas
    0.77
     fresher
    0.77
    Activations Density 0.132%

    No Known Activations