© 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. 11-GEMMASCOPE-RES-16K
    6. 4725
    Prev
    Next
    INDEX
    Explanations

    adjectives describing quantity or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -------
    -0.57
    锈钢
    -0.52
     kaarangay
    -0.46
     Wikimedijinoj
    -0.40
    Underground
    -0.39
    Jeografia
    -0.38
    This
    -0.38
    mêmes
    -0.38
     mandatario
    -0.37
     AUSSI
    -0.36
    POSITIVE LOGITS
     auroit
    0.63
     pouvoit
    0.63
     utafitiHapana
    0.58
     feroit
    0.57
     avoient
    0.57
     doInBackground
    0.54
     houſe
    0.53
     ainfi
    0.50
     purpoſe
    0.48
    BibitemShut
    0.48
    Activations Density 0.730%

    No Known Activations