© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5215
    Prev
    Next
    INDEX
    Explanations

    references to incidents involving death or bodies being discovered

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

    "Found" or "discovered"

    np_acts-logits-general · gemini-2.0-flash

    found by or collected in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    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
    -0.73
     AssemblyCulture
    -0.67
     transfieras
    -0.61
     pinulongan
    -0.60
     CreateTagHelper
    -0.56
    BeginContext
    -0.52
    hilangan
    -0.52
    Diweddarwch
    -0.52
    󠁬
    -0.52
    RenderAtEndOf
    -0.51
    POSITIVE LOGITS
     discovered
    0.62
     noticed
    0.57
     обнаружи
    0.53
     noticing
    0.53
     entdeckt
    0.49
     discovering
    0.49
    discovered
    0.48
     Discovered
    0.47
    發現
    0.47
    noticed
    0.46
    Activations Density 0.280%

    No Known Activations