© 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. 4921
    Prev
    Next
    INDEX
    Explanations

    key programming concepts and terminology in Spanish

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

    Spanish language text.

    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
    pecabe
    -1.48
     navideño
    -1.45
     desmotivaciones
    -1.41
     romántico
    -1.41
     británico
    -1.37
     venezolano
    -1.35
     productivo
    -1.33
     prohibido
    -1.31
     asesinado
    -1.31
     literario
    -1.30
    POSITIVE LOGITS
     lo
    0.52
     peg
    0.49
     retra
    0.48
     conf
    0.47
     inv
    0.47
     si
    0.47
     por
    0.47
     de
    0.46
     en
    0.45
     tan
    0.45
    Activations Density 0.159%

    No Known Activations