© 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. 11126
    Prev
    Next
    INDEX
    Explanations

    terms related to non-profit or non-commercial contexts

    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
     desigual
    -0.42
     úteis
    -0.38
    ***********/
    -0.38
     Polsek
    -0.37
    expliquer
    -0.36
     grabación
    -0.36
     câmbio
    -0.35
    ViewBag
    -0.35
    BagLayout
    -0.35
     bandeira
    -0.34
    POSITIVE LOGITS
     Non
    0.83
     NON
    0.71
    Non
    0.71
     non
    0.71
    non
    0.64
     Nons
    0.62
    httphttps
    0.62
    enumii
    0.60
    NON
    0.59
    nons
    0.56
    Activations Density 0.220%

    No Known Activations