© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 2968
    Prev
    Next
    INDEX
    Explanations

    parameters and values associated with video IDs and metadata within a coding or documentation context

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    URL parameters and query strings in YouTube links.

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    yourself
    -1.06
     yourselves
    -1.05
     yourself
    -1.05
     myſelf
    -1.03
    herself
    -1.02
     himſelf
    -1.01
     ourselves
    -1.00
     Himself
    -1.00
     herself
    -0.98
    himself
    -0.96
    POSITIVE LOGITS
    5
    0.39
    7
    0.36
    6
    0.35
    3
    0.35
    9
    0.34
    1
    0.33
    ']),
    0.32
    8
    0.32
    ]');
    0.31
    ea
    0.31
    Activations Density 0.451%

    No Known Activations