© 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. 15-GEMMASCOPE-RES-16K
    11. 4022
    Prev
    Next
    INDEX
    Explanations

    assertions or claims about actions or experiences, particularly those involving moral or ethical implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 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
     inflater
    -0.55
    IMPORTED
    -0.54
    VersionUID
    -0.47
    flashdata
    -0.44
    stdc
    -0.44
    aven
    -0.43
    disposing
    -0.42
    tonode
    -0.42
     viewType
    -0.41
    Enlaces
    -0.41
    POSITIVE LOGITS
     genuine
    1.55
     genuinely
    1.52
    genuine
    1.31
     fakty
    1.29
    actual
    1.27
     actual
    1.23
     réel
    1.22
     tatsächlich
    1.20
    genu
    1.20
    Actual
    1.20
    Activations Density 0.327%

    No Known Activations