© 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. 2460
    Prev
    Next
    INDEX
    Explanations

    text describing complexity in various contexts

    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
    balleur
    -0.39
     avoient
    -0.38
     some
    -0.35
    实话
    -0.32
    夠
    -0.32
     fusca
    -0.31
     futuro
    -0.30
    IntoConstraints
    -0.30
    soldiers
    -0.30
     élève
    -0.30
    POSITIVE LOGITS
     complex
    3.50
     Complex
    3.13
    Complex
    3.11
    complex
    3.09
     complicated
    2.92
     COMPLEX
    2.83
     complexe
    2.61
     complexo
    2.58
    COMPLEX
    2.55
     komplex
    2.53
    Activations Density 0.154%

    No Known Activations