© 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 EvalsExportsAPI 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. 2094
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and calculations

    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
     ſind
    -0.93
    ロウィン
    -0.90
     ſei
    -0.89
     ſever
    -0.89
    iſchen
    -0.87
     myſelf
    -0.86
     ſch
    -0.85
     zwiſchen
    -0.83
     ſche
    -0.83
     beſte
    -0.83
    POSITIVE LOGITS
    ↵↵
    0.30
    ing
    0.29
    。
    0.24
    ere
    0.23
    underbrace
    0.23
    ำ
    0.22
    er
    0.22
    日
    0.22
    r
    0.22
    w
    0.22
    Activations Density 0.147%

    No Known Activations