© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 15914
    Prev
    Next
    INDEX
    Explanations

    strong adjectives and related terms indicating robustness or resilience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MathML
    -0.39
     насељу
    -0.38
     sorts
    -0.35
    atalos
    -0.34
     umge
    -0.34
    Nationalité
    -0.33
     Umgang
    -0.31
    SPATH
    -0.31
     taxas
    -0.30
     Vergnügen
    -0.30
    POSITIVE LOGITS
     willed
    0.84
     Weak
    0.80
    Weak
    0.74
    weak
    0.69
     weak
    0.69
    STRONG
    0.66
     💪
    0.65
    Strong
    0.61
     Strong
    0.61
     weaker
    0.61
    Activations Density 0.166%

    No Known Activations