© 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. 3-GEMMASCOPE-RES-16K
    11. 7022
    Prev
    Next
    INDEX
    Explanations

    instances of the word "firm" or its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TargetException
    -0.63
    ContentLoaded
    -0.61
    pagation
    -0.60
    HasAnnotation
    -0.60
    ContentAlignment
    -0.58
    Източници
    -0.58
    ↹
    -0.58
    ographical
    -0.58
    сылкі
    -0.56
     Saturation
    -0.56
    POSITIVE LOGITS
     firm
    4.19
     Firm
    3.70
    Firm
    3.66
    firm
    3.63
     FIRM
    3.23
     firms
    3.11
     Firms
    2.88
     firme
    2.63
     firmer
    2.61
     firmness
    2.33
    Activations Density 0.097%

    No Known Activations