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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 13713
    Prev
    Next
    INDEX
    Explanations

    phrases indicating transitions or entries into specific situations or contexts

    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
    WebVitals
    -0.48
     referrerpolicy
    -0.48
     berp
    -0.48
    şört
    -0.47
    ніципалі
    -0.44
    pecies
    -0.41
    mbals
    -0.41
    getDescriptor
    -0.40
     társ
    -0.40
    anwal
    -0.40
    POSITIVE LOGITS
     into
    1.23
    Into
    1.08
    into
    1.07
     Into
    1.05
     INTO
    0.98
    INTO
    0.87
     vào
    0.59
     hinein
    0.55
    תוך
    0.49
     vao
    0.47
    Activations Density 0.258%

    No Known Activations