© 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. 9472
    Prev
    Next
    INDEX
    Explanations

    legal and medical references, particularly in regards to observations and evaluations related to trials and evidence

    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
     EconPapers
    -0.49
    éril
    -0.39
     jao
    -0.37
    contentLoaded
    -0.36
    フィシャル
    -0.32
    ፩
    -0.30
    שמי
    -0.30
    ycznie
    -0.30
    zyms
    -0.29
    も同じ
    -0.28
    POSITIVE LOGITS
     combined
    2.88
     coupled
    2.73
    combined
    2.39
     Combined
    2.27
     Coupled
    2.22
    coupled
    2.19
    Combined
    2.14
     paired
    2.09
     combinado
    2.08
     COMBIN
    1.95
    Activations Density 1.617%

    No Known Activations