© 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. 40-GEMMASCOPE-RES-16K
    6. 6096
    Prev
    Next
    INDEX
    Explanations

    words related to raw or unprocessed materials, particularly in the context of biological and environmental subjects

    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
    ️
    -0.49
    ยาว
    -0.44
    BeginInit
    -0.43
    ยัง
    -0.40
    ViewFeatures
    -0.40
    erol
    -0.38
    Bakgrunnsstoff
    -0.37
    +#+
    -0.37
    ย
    -0.36
    ória
    -0.36
    POSITIVE LOGITS
    wwww
    0.72
    wwwww
    0.69
    ww
    0.68
    wwwwwwww
    0.67
    ed
    0.63
    adays
    0.63
    esome
    0.61
    ell
    0.60
    orld
    0.59
    WWWW
    0.58
    Activations Density 0.370%

    No Known Activations