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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 16250
    Prev
    Next
    INDEX
    Explanations

    calls to action, particularly those starting with "come."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.80
    IntoConstraints
    -0.75
    Cyfeiriadau
    -0.60
    ragalactic
    -0.58
    Personendaten
    -0.54
     ſa
    -0.52
     TextAppearance
    -0.52
     ligiloj
    -0.52
     SwitchCompat
    -0.51
     државе
    -0.49
    POSITIVE LOGITS
     come
    1.87
    Come
    1.84
     Come
    1.81
    come
    1.76
     COME
    1.59
    COME
    1.41
    comed
    0.83
     comeback
    0.76
     Comeback
    0.75
     comes
    0.73
    Activations Density 0.099%

    No Known Activations