© 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. 14814
    Prev
    Next
    INDEX
    Explanations

    terms related to investigations and witness testimonies

    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
    :✨
    -0.68
    principalTable
    -0.67
    andExpect
    -0.63
     useDispatch
    -0.61
    ⓧ
    -0.59
    ifest
    -0.59
    omitempty
    -0.59
    esModule
    -0.59
    StoryboardSegue
    -0.59
     spesies
    -0.58
    POSITIVE LOGITS
     subpoena
    0.65
     documents
    0.63
     FBI
    0.61
     emails
    0.59
     Ohr
    0.59
    documents
    0.57
     investigators
    0.57
    Emails
    0.57
     subpo
    0.55
     Mueller
    0.55
    Activations Density 0.667%

    No Known Activations