© 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. 41-GEMMASCOPE-RES-16K
    11. 4894
    Prev
    Next
    INDEX
    Explanations

    names and proper nouns, particularly those related to people or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    le
    -0.66
     resourceCulture
    -0.63
     للاسماء
    -0.57
     noDo
    -0.55
    förm
    -0.50
    further
    -0.47
    förmig
    -0.47
    f
    -0.46
    flip
    -0.46
    för
    -0.44
    POSITIVE LOGITS
    ので
    0.53
    ld
    0.52
    las
    0.49
    ldes
    0.41
    ldon
    0.41
    ldorf
    0.40
    lda
    0.40
    ade
    0.39
    lasi
    0.39
    lying
    0.38
    Activations Density 0.200%

    No Known Activations