© 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-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 22090
    Prev
    Next
    INDEX
    Explanations

    terms and phrases that indicate weakness or a lesser degree of strength

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.75
     Mundi
    -0.73
    Portale
    -0.71
     ocurrido
    -0.68
     Tuttle
    -0.67
    Hozzáférés
    -0.65
    udur
    -0.65
    กรม
    -0.64
    rfloor
    -0.63
     jette
    -0.63
    POSITIVE LOGITS
     Weak
    1.56
    weak
    1.36
     weak
    1.35
    Weak
    1.34
    Weaknesses
    1.24
    弱
    1.14
     weakly
    1.08
     weakness
    1.07
    WEAK
    1.03
     weaker
    1.02
    Activations Density 0.010%

    No Known Activations