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

    Neuronpedia

    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. 31-GEMMASCOPE-RES-16K
    11. 1527
    Prev
    Next
    INDEX
    Explanations

    references to changes and addressing issues in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    conditional statements and logical connectives that introduce consequences or results.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.47
    Personendaten
    -0.45
    []);
    -0.43
    [])
    -0.42
    AsUp
    -0.41
     demografica
    -0.41
    }}/>
    -0.40
    AccessorTable
    -0.39
     StatelessWidget
    -0.38
    fjspx
    -0.38
    POSITIVE LOGITS
     everything
    3.89
    everything
    3.61
     Everything
    3.42
    Everything
    3.41
     EVERYTHING
    2.83
     tudo
    2.81
     wszystko
    2.50
     všetko
    2.39
     alles
    2.33
     всичко
    2.30
    Activations Density 0.625%

    No Known Activations