© 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. 23-GEMMASCOPE-RES-16K
    11. 8054
    Prev
    Next
    INDEX
    Explanations

    phrases related to achieving desired outcomes or results in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vite
    -0.30
     trav
    -0.30
    基
    -0.30
     propen
    -0.30
     CK
    -0.30
     she
    -0.30
     other
    -0.29
    écoute
    -0.29
     sich
    -0.29
    頃から
    -0.29
    POSITIVE LOGITS
     achieved
    0.82
     achieve
    0.80
     achieves
    0.78
    achieved
    0.78
    Achie
    0.75
     erzielen
    0.73
     results
    0.73
     uzyskać
    0.72
     uzys
    0.69
    achieve
    0.69
    Activations Density 0.732%

    No Known Activations