© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4094
    Prev
    Next
    INDEX
    Explanations

    details related to criminal activities and forensic evidence

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

    surrounding discovery of a body

    np_acts-logits-general · gemini-2.0-flash

    bodies discovered at scenes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.74
    fjspx
    -0.74
    thâu
    -0.69
     linkovi
    -0.66
     tartalomajánló
    -0.64
    SBATCH
    -0.63
     CreateTagHelper
    -0.62
     deafness
    -0.62
    HandlerContext
    -0.62
    RectangleBorder
    -0.61
    POSITIVE LOGITS
     evidence
    0.82
     autopsy
    0.73
     forensic
    0.73
     wreckage
    0.68
     scene
    0.66
     Forensic
    0.66
    Forensic
    0.65
     discovery
    0.65
     bodies
    0.64
    Evidence
    0.64
    Activations Density 0.328%

    No Known Activations