© 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. 18-GEMMASCOPE-RES-16K
    6. 3904
    Prev
    Next
    INDEX
    Explanations

    references to companionship and social connections

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

    location/position

    np_acts-logits-general · gemini-2.0-flash

    beside or next to

    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
    ñal
    -0.53
     EconPapers
    -0.48
     patern
    -0.47
    veland
    -0.47
     Labour
    -0.47
    reconnect
    -0.47
    Cyfeiriadau
    -0.46
    EnableWeb
    -0.44
    kennt
    -0.44
    consistency
    -0.43
    POSITIVE LOGITS
     beside
    1.39
     side
    1.21
     Beside
    1.11
     bedside
    1.07
    side
    1.04
     sides
    1.03
    Side
    1.01
     côtés
    0.99
     accanto
    0.98
     alongside
    0.97
    Activations Density 0.101%

    No Known Activations