© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 11016
    Prev
    Next
    INDEX
    Explanations

    technical specifications and features related to engines and performance

    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
     CURIAM
    -0.49
    //
    -0.44
    Domino
    -0.43
    +:+
    -0.43
    transQ
    -0.41
    recated
    -0.41
    __':
    -0.41
    IUrlHelper
    -0.41
     judiciales
    -0.40
     clipboard
    -0.40
    POSITIVE LOGITS
     diesel
    0.91
     Diesel
    0.89
    Diesel
    0.82
     дизе
    0.78
    diesel
    0.77
     DIES
    0.74
     biodiesel
    0.61
     Cummins
    0.60
     Dies
    0.59
     dies
    0.58
    Activations Density 0.178%

    No Known Activations