© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 4033
    Prev
    Next
    INDEX
    Explanations

    the presence of actions and descriptions related to communication and information sharing

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

    Attribution of a quote

    np_acts-logits-general · gemini-2.0-flash

    reporting or stating actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nitř
    -0.45
    inander
    -0.45
    currentColor
    -0.42
     refleja
    -0.40
    łos
    -0.40
    exao
    -0.40
     vindo
    -0.40
     admiten
    -0.40
    址
    -0.40
     currency
    -0.39
    POSITIVE LOGITS
     himself
    1.50
    himself
    1.13
     his
    1.11
    httphttps
    0.88
     Himself
    0.84
     defaultstate
    0.83
    his
    0.82
    BeginContext
    0.81
     {}));
    0.79
     herself
    0.78
    Activations Density 0.824%

    No Known Activations