© 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. 12-GEMMASCOPE-RES-16K
    6. 1820
    Prev
    Next
    INDEX
    Explanations

    references to spatial orientations and arrangements, particularly in horizontal and vertical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nadores
    -0.41
     Pep
    -0.39
     initWith
    -0.39
     tacón
    -0.39
    usiai
    -0.38
     offici
    -0.38
    Naissance
    -0.38
     behö
    -0.37
     Hecho
    -0.37
     pep
    -0.36
    POSITIVE LOGITS
     horizontal
    1.95
     Horizontal
    1.81
    horizontal
    1.77
    Horizontal
    1.77
     horizontally
    1.65
     orizz
    1.45
     horizont
    1.45
     vertical
    1.43
     Vertical
    1.41
    vertical
    1.36
    Activations Density 0.214%

    No Known Activations