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

    Neuronpedia

    Jacobian LensNEW
    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. 15-GEMMASCOPE-RES-16K
    11. 735
    Prev
    Next
    INDEX
    Explanations

    placeholders or markup indicators in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dourada
    -0.61
     signifikan
    -0.60
     gitara
    -0.54
     aikaa
    -0.53
    ulemon
    -0.52
    ativna
    -0.52
    dotta
    -0.52
    ikka
    -0.51
     cielos
    -0.51
    󠁴
    -0.51
    POSITIVE LOGITS
     inder
    0.51
    Hozzáférés
    0.49
     Houſe
    0.48
     whofe
    0.47
     corne
    0.44
    IVEREF
    0.44
    enumi
    0.44
     "":
    0.43
    "}>
    0.43
     halve
    0.43
    Activations Density 0.160%

    No Known Activations