© 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. 22-GEMMASCOPE-RES-16K
    11. 1818
    Prev
    Next
    INDEX
    Explanations

    details related to criminal investigations and evidence collection

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

    crime scene investigation

    np_acts-logits-general · gemini-2.0-flash

    forensic evidence collection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.68
     AppComponent
    -0.60
    istoitu
    -0.58
     otomatig
    -0.56
    ViewInit
    -0.54
    Portail
    -0.53
    ftagPool
    -0.52
     waveguide
    -0.51
    AutoScaleMode
    -0.50
     strto
    -0.50
    POSITIVE LOGITS
     forensic
    1.20
     investigators
    1.06
     Forensic
    1.03
    Investigators
    1.01
    Forensic
    1.00
     detectives
    0.97
     Investigators
    0.96
     autopsy
    0.94
     Crime
    0.94
     crime
    0.90
    Activations Density 0.635%

    No Known Activations