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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 11624
    Prev
    Next
    INDEX
    Explanations

    terms related to communication and interpersonal relationships

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

    followed by verbs of cognition/perception

    np_acts-logits-general · gemini-2.0-flash

    what someone knows

    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
    RenderAtEndOf
    -0.61
    ScopeManager
    -0.49
     Einwilligung
    -0.47
    Filmographie
    -0.47
     INT
    -0.47
    DEP
    -0.44
    发表于
    -0.44
    Eloquent
    -0.44
    Int
    -0.44
     AppCompat
    -0.43
    POSITIVE LOGITS
     sees
    0.95
     knows
    0.94
     know
    0.89
     understand
    0.89
     hears
    0.87
     understands
    0.84
     see
    0.83
     KNOW
    0.81
    Know
    0.79
    Understand
    0.77
    Activations Density 0.345%

    No Known Activations