© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 59745
    Prev
    Next
    INDEX
    Explanations

    references to sexual abuse within religious institutions and discussions around their prevention and handling

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

    Police Clearance Certificate, church policy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.69
    новништво
    -0.63
    ngrx
    -0.53
    VideoCapture
    -0.52
    webElementGuid
    -0.51
    󠁮
    -0.49
     bershka
    -0.49
    ruptedException
    -0.49
     kasarigan
    -0.47
    +#+#
    -0.47
    POSITIVE LOGITS
     sportiva
    0.41
     goederen
    0.40
     gedrag
    0.39
     cucchia
    0.36
     gebou
    0.35
     quedo
    0.35
     Recreation
    0.35
     loisirs
    0.34
     aanbod
    0.33
     organisasi
    0.33
    Activations Density 0.159%

    No Known Activations