© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5771
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "select" or variations of it in code and query contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
    toCharArray
    -0.74
    Enlaces
    -0.70
     թվական
    -0.65
    intellij
    -0.64
     Audiodateien
    -0.64
    PMailer
    -0.63
    
    -0.61
    Ārējās
    -0.61
    CFLAGS
    -0.61
    BufferException
    -0.60
    POSITIVE LOGITS
    select
    2.52
    Select
    2.52
     Select
    2.52
     select
    2.32
     SELECT
    2.23
    SELECT
    2.09
     selects
    1.72
     selectAll
    1.51
    Sele
    1.42
     selecting
    1.40
    Activations Density 0.066%

    No Known Activations