© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 2930
    Prev
    Next
    INDEX
    Explanations

    references to extremist groups and their activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to extremist groups and conflict situations

    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
    nthetic
    -0.42
     svolta
    -0.41
     suivre
    -0.40
    PLEMENT
    -0.40
    timewa
    -0.40
     geprek
    -0.39
    veti
    -0.39
    йки
    -0.38
    GEBURTS
    -0.38
    いただいて
    -0.38
    POSITIVE LOGITS
    MessageTagHelper
    0.81
     OMITBAD
    0.80
    WebServlet
    0.71
     evil
    0.69
     SqlCommand
    0.68
    SourceChecksum
    0.67
     scum
    0.67
     virulence
    0.66
    áctenos
    0.66
     threats
    0.65
    Activations Density 0.540%

    No Known Activations