© 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. 13863
    Prev
    Next
    INDEX
    Explanations

    elements related to HTML structure and attributes

    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
    ########.
    -1.12
     queſta
    -1.08
    ſicht
    -0.98
    ValueStyle
    -0.95
    iſchen
    -0.93
    ſſung
    -0.93
    <pad>
    -0.92
    featureID
    -0.91
    <unused16>
    -0.91
    <unused17>
    -0.91
    POSITIVE LOGITS
    <
    1.02
     <
    0.88
    <!--
    0.54
    <!--<
    0.45
     <!--
    0.40
    &
    0.40
     &
    0.34
    </
    0.33
    <tr>
    0.32
    ↵
    0.31
    Activations Density 0.320%

    No Known Activations