© 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. 8379
    Prev
    Next
    INDEX
    Explanations

    programming code structures, such as variable assignments and control flow elements

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

    structural delimiters and assignment operators in code syntax.

    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
     bloques
    -0.52
     blocco
    -0.45
    الإنجليزية
    -0.45
     actitudes
    -0.41
     block
    -0.41
    ttemberg
    -0.40
     blok
    -0.40
     berdua
    -0.40
     duele
    -0.40
     genaue
    -0.40
    POSITIVE LOGITS
     Single
    0.46
    "]).
    0.45
    "]),
    0.43
     Roskov
    0.42
    )?
    0.39
    nad
    0.39
     Tea
    0.39
     Bunch
    0.38
    )\}
    0.38
     Supers
    0.38
    Activations Density 0.509%

    No Known Activations