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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 5916
    Prev
    Next
    INDEX
    Explanations

    occurrences of the abbreviation "fa" related to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bezir
    -0.35
    zupeł
    -0.34
    rboles
    -0.34
     picioare
    -0.33
     chłop
    -0.33
     unterkunft
    -0.33
    oredCriteria
    -0.33
    Życiorys
    -0.32
     poster
    -0.32
     Wahrheit
    -0.32
    POSITIVE LOGITS
     fa
    3.42
     Fa
    2.39
    Fa
    2.31
    fa
    2.16
     FA
    1.48
    FA
    1.42
     Fai
    1.12
     faa
    1.05
     фа
    1.01
     Faul
    1.00
    Activations Density 0.082%

    No Known Activations