© 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. 7-GEMMASCOPE-RES-16K
    11. 12839
    Prev
    Next
    INDEX
    Explanations

    concepts related to overall effectiveness or performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.49
    principalColumn
    -0.44
     geographic
    -0.42
    IntoConstraints
    -0.42
     AttributeSet
    -0.39
     geography
    -0.38
    SBATCH
    -0.36
    专利
    -0.36
     BorderSide
    -0.36
    PathVariable
    -0.35
    POSITIVE LOGITS
     Overall
    1.21
     overall
    1.20
    Overall
    1.19
    overall
    1.18
     total
    1.08
     Total
    1.08
    total
    1.06
     Gesamt
    1.03
    Total
    0.99
    Gesamt
    0.97
    Activations Density 0.613%

    No Known Activations