© 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-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 7033
    Prev
    Next
    INDEX
    Explanations

    numerical values and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.52
     فريبيس
    -0.51
    Datuak
    -0.50
     OMITBAD
    -0.50
     tartalomajánló
    -0.49
    RectangleBorder
    -0.48
    fromCharCode
    -0.45
     TestBed
    -0.44
    原始内容存档于
    -0.44
     EconPapers
    -0.43
    POSITIVE LOGITS
    zeptember
    0.49
     namanya
    0.38
    ciaż
    0.37
     December
    0.36
     September
    0.36
     Rudolph
    0.36
    Sucesor
    0.36
     cuar
    0.35
    December
    0.35
     October
    0.35
    Activations Density 0.276%

    No Known Activations