© 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. 7453
    Prev
    Next
    INDEX
    Explanations

    technical terms related to procedures and actions in machinery or engineering contexts

    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
    》.
    -0.41
    انتهای
    -0.38
    )}.
    -0.34
     bezeichneter
    -0.34
    }.
    -0.33
     Sees
    -0.33
     resourceCulture
    -0.32
    ”.
    -0.31
    ".
    -0.31
    ”!
    -0.30
    POSITIVE LOGITS
     will
    1.09
    서는
    1.06
     would
    1.00
    리는
    0.99
     was
    0.97
    지는
    0.94
     seems
    0.93
     may
    0.92
     ayaa
    0.92
     cannot
    0.91
    Activations Density 3.906%

    No Known Activations