© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 795
    Prev
    Next
    INDEX
    Explanations

    warning phrases or terms related to caution and careful handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HttpNotFound
    -0.39
     holl
    -0.31
    geblich
    -0.31
     ErrIntOverflow
    -0.30
     насељу
    -0.28
    stående
    -0.27
    BeginContext
    -0.27
     paix
    -0.26
     odds
    -0.26
    Objetivo
    -0.26
    POSITIVE LOGITS
     careful
    2.30
     caution
    2.13
     Careful
    2.02
     care
    2.00
     cuidado
    1.98
    Careful
    1.88
     carefully
    1.81
    caution
    1.80
    care
    1.79
     Caution
    1.79
    Activations Density 0.461%

    No Known Activations