© 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 - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 14886
    Prev
    Next
    INDEX
    Explanations

    terms related to safe environments, particularly in contexts involving support for individuals affected by abuse or violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.82
    StoryboardSegue
    -0.76
     الرياضيه
    -0.71
    렷
    -0.71
    GraphicsUnit
    -0.65
     ujednoznacz
    -0.65
     otomatig
    -0.65
     onData
    -0.57
    HideFlags
    -0.57
     kaarangay
    -0.56
    POSITIVE LOGITS
     environment
    3.16
    environment
    2.66
     environments
    2.62
     Environment
    2.47
     ENVIRONMENT
    2.33
    Environment
    2.30
     environnement
    2.19
     ambiente
    2.18
     Environments
    2.17
    环境
    2.15
    Activations Density 0.702%

    No Known Activations