© 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. 33-GEMMASCOPE-RES-16K
    11. 5669
    Prev
    Next
    INDEX
    Explanations

    procedural language and methodology descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.44
     förr
    -0.42
    
    -0.39
     Grüsse
    -0.39
    awaiter
    -0.37
    ltä
    -0.36
     automatiques
    -0.35
     Erhaltung
    -0.35
     despacho
    -0.34
     öffentliche
    -0.34
    POSITIVE LOGITS
     modified
    2.56
     modifications
    2.27
     modification
    2.22
    modified
    2.19
     Modified
    2.09
     modific
    2.03
    Modified
    2.02
     Modifications
    1.99
     modify
    1.92
     Modification
    1.91
    Activations Density 1.316%

    No Known Activations