© 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. 12-GEMMASCOPE-RES-16K
    11. 10697
    Prev
    Next
    INDEX
    Explanations

    beliefs or assertions about information and the act of recalling details

    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
     zrozum
    -0.43
     llorar
    -0.43
    enfance
    -0.42
     dedicar
    -0.42
     asegurarse
    -0.41
     Sénat
    -0.41
     médicaux
    -0.41
     Româ
    -0.41
     puissiez
    -0.40
     enfance
    -0.40
    POSITIVE LOGITS
     ModelExpression
    0.59
    makeConstraints
    0.57
    Javadoc
    0.52
    rungsseite
    0.50
     somewhere
    0.49
     TestBed
    0.49
    PropertyChanging
    0.48
     Somewhere
    0.46
     "..\..\
    0.45
     flo
    0.44
    Activations Density 0.330%

    No Known Activations