© 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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 9747
    Prev
    Next
    INDEX
    Explanations

    instances of the word "this" and its variations

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

    the beginning of a new article or section marked by the word "This".

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.65
     Италијани
    -0.54
    Havolalar
    -0.52
    thâu
    -0.51
    ArrowToggle
    -0.50
    SharedDtor
    -0.50
     <>",
    -0.49
    !*\
    -0.49
    UserScript
    -0.49
     lenker
    -0.49
    POSITIVE LOGITS
     is
    1.21
     was
    0.81
     merupakan
    0.71
     happens
    0.67
     bukanlah
    0.65
     isn
    0.65
     may
    0.63
    是一個
    0.62
    したのは
    0.60
     reminds
    0.60
    Activations Density 0.299%

    No Known Activations