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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8525
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence or absence of elements in experimental contexts

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

    "presence" after "the"

    np_acts-logits-general · gemini-2.0-flash

    presence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.58
    fillType
    -0.57
     Unmarshal
    -0.57
    árl
    -0.57
     Becoming
    -0.51
    becoming
    -0.50
     Pingback
    -0.50
    ifun
    -0.50
    ViewImports
    -0.50
    LEncoder
    -0.49
    POSITIVE LOGITS
     presence
    3.40
    presence
    2.95
     présence
    2.94
     Presence
    2.76
     presencia
    2.62
    Presence
    2.56
     presenza
    2.49
     presença
    2.44
     aanwezig
    2.20
     kehadiran
    2.02
    Activations Density 0.595%

    No Known Activations