© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 7759
    Prev
    Next
    INDEX
    Explanations

    the presence of goals and aims articulated in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Franke
    -0.74
     McCarty
    -0.70
     Dreyfus
    -0.69
    "}}
    -0.69
    ++++++++++++++++
    -0.68
    ogeneous
    -0.68
     Schroeder
    -0.67
    aurus
    -0.67
    Stefano
    -0.62
    fucker
    -0.62
    POSITIVE LOGITS
     AIM
    1.44
     Aims
    1.43
    Aims
    1.32
     Aim
    1.29
    AIM
    1.25
    Aim
    1.18
     aims
    1.16
     Aimee
    1.09
    aim
    1.09
     aimed
    0.99
    Activations Density 0.010%

    No Known Activations