© 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. 7849
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to the preservation and analysis of starch and its properties

    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
     slammed
    -0.44
     Regulation
    -0.42
     незавершена
    -0.39
    Regulation
    -0.39
     kaarangay
    -0.38
    DSM
    -0.38
     Reception
    -0.38
     linkovi
    -0.38
     smacked
    -0.37
    ünsche
    -0.37
    POSITIVE LOGITS
     decay
    1.60
     deterioration
    1.42
     degradation
    1.41
     Decay
    1.39
     decaying
    1.30
     decomposition
    1.28
     degrade
    1.27
    decay
    1.26
     decayed
    1.25
     rotting
    1.24
    Activations Density 0.680%

    No Known Activations