© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 3229
    Prev
    Next
    INDEX
    Explanations

    mentions of algorithms or algorithm-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idency
    -0.40
     residency
    -0.37
     steady
    -0.36
    besch
    -0.36
    leness
    -0.35
    torie
    -0.35
    too
    -0.35
    kinson
    -0.34
     branding
    -0.34
     Copyright
    -0.34
    POSITIVE LOGITS
     lenguaje
    0.82
    Algorithm
    0.81
     Algorithm
    0.80
     language
    0.78
    Algorithms
    0.77
     Algorithms
    0.74
     algorithm
    0.74
     LANGUAGE
    0.74
    Autoritní
    0.71
    algorithm
    0.69
    Activations Density 0.149%

    No Known Activations