© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 5497
    Prev
    Next
    INDEX
    Explanations

    terms related to licensing and copyright information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Lif
    -0.93
     Leaders
    -0.85
    Lives
    -0.85
     Leads
    -0.84
     Letters
    -0.84
     Laws
    -0.84
    Laws
    -0.84
     Lives
    -0.82
    LAST
    -0.82
    Lear
    -0.82
    POSITIVE LOGITS
     l
    0.53
     le
    0.48
     ли
    0.47
     լ
    0.47
     הל
    0.47
     lauf
    0.46
     lake
    0.43
     lé
    0.42
     la
    0.42
     lakh
    0.42
    Activations Density 2.253%

    No Known Activations