© 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. 34-GEMMASCOPE-RES-16K
    11. 2668
    Prev
    Next
    INDEX
    Explanations

    references to prior research or studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thereafter
    -0.44
    今後も
    -0.43
     further
    -0.41
     künftig
    -0.40
     zukünf
    -0.40
    接下来
    -0.39
     later
    -0.39
    soon
    -0.39
     future
    -0.38
    接下来的
    -0.38
    POSITIVE LOGITS
    itisation
    0.58
     Chwiliwch
    0.57
     generations
    0.57
     successes
    0.56
     editions
    0.54
     incarnation
    0.54
     unsuccessful
    0.54
    WithIOException
    0.52
     versions
    0.52
     incar
    0.52
    Activations Density 0.262%

    No Known Activations