© 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. 22-GEMMASCOPE-RES-16K
    6. 5702
    Prev
    Next
    INDEX
    Explanations

    instances of reunions or reconnections between individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.45
     rall
    -0.43
    </>
    -0.42
     disambiguazione
    -0.41
     boli
    -0.39
    bių
    -0.37
    -------------</
    -0.37
    CDCl
    -0.37
    cyklo
    -0.36
    Referencie
    -0.36
    POSITIVE LOGITS
     finalement
    0.69
     finally
    0.68
     finalmente
    0.64
     eventually
    0.62
     akhirnya
    0.61
     ultimately
    0.59
     schließlich
    0.58
     uiteindelijk
    0.57
    無事に
    0.56
    finally
    0.56
    Activations Density 0.603%

    No Known Activations