Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 2478
    Prev
    Next
    INDEX
    Explanations

    conditional statements and requirements related to usage and functionality in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Geſch
    -0.86
     increí
    -0.77
     Waſſer
    -0.77
    ⟬
    -0.73
    ſcher
    -0.72
    ſehen
    -0.71
    iſchen
    -0.71
     Geiſt
    -0.71
    mpagne
    -0.70
    initWithFrame
    -0.70
    POSITIVE LOGITS
    3
    0.35
    作
    0.34
    1
    0.33
    4
    0.32
    ↵↵
    0.30
    <
    0.30
    I
    0.30
    2
    0.29
    As
    0.29
    0
    0.28
    Activations Density 0.769%

    No Known Activations