Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 1063
    Prev
    Next
    INDEX
    Explanations

    references to job losses and significant local events

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

    Northern Ireland place names

    np_acts-logits-general · gemini-2.0-flash

    Ballymena

    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
    spesies
    -0.58
    ScopeManager
    -0.56
    \}^{
    -0.52
     étions
    -0.51
    uyler
    -0.51
    Xf
    -0.50
    Ừ
    -0.50
    Personensuche
    -0.50
    orsing
    -0.49
     CPF
    -0.49
    POSITIVE LOGITS
     Belfast
    1.07
    Belfast
    0.99
     belf
    0.84
     Antrim
    0.79
     Ulster
    0.76
     Derry
    0.75
    NI
    0.70
     NI
    0.68
    Datuak
    0.66
    derry
    0.64
    Activations Density 0.109%

    No Known Activations