© 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. 38-GEMMASCOPE-RES-16K
    11. 12378
    Prev
    Next
    INDEX
    Explanations

    references to specific groups or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tadi
    -0.40
     Aragón
    -0.39
     maternidade
    -0.36
     Meksika
    -0.35
    Empereur
    -0.34
     comigo
    -0.33
     and
    -0.32
     Atlántico
    -0.32
     üzere
    -0.31
    pulseira
    -0.31
    POSITIVE LOGITS
    ########.
    0.94
    OGND
    0.86
    GOTREF
    0.79
     otomatig
    0.79
     snippetHide
    0.77
    enderror
    0.76
     MainAxisSize
    0.73
     ligiloj
    0.73
    DockStyle
    0.73
    ſcher
    0.73
    Activations Density 1.338%

    No Known Activations