© 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. 24-GEMMASCOPE-RES-16K
    11. 2477
    Prev
    Next
    INDEX
    Explanations

    phrases related to secrecy and hidden actions

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

    "Behind" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    behind closed doors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    Tikang
    -0.71
    CppMethod
    -0.67
     alrededores
    -0.63
     Chwiliwch
    -0.62
    bootstrapcdn
    -0.59
     hâte
    -0.59
    mergeFrom
    -0.56
     pinulongan
    -0.55
     noqa
    -0.55
     préciser
    -0.54
    POSITIVE LOGITS
     scenes
    1.30
    scenes
    1.10
     closed
    1.05
     Scenes
    1.02
    Scenes
    1.02
    closed
    0.89
     curtain
    0.89
     bars
    0.83
     curtains
    0.83
     Closed
    0.82
    Activations Density 0.077%

    No Known Activations