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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3446
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the passage of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zzleHttp
    -0.40
    insatz
    -0.38
    ailleurs
    -0.37
     inyección
    -0.37
    WriteTagHelper
    -0.37
    før
    -0.36
     linkovi
    -0.34
    うら
    -0.34
    énario
    -0.34
    PÁG
    -0.34
    POSITIVE LOGITS
     over
    0.76
     hinweg
    0.61
     across
    0.60
    throughout
    0.60
     throughout
    0.59
    across
    0.57
     spanning
    0.56
     spans
    0.55
    SOUNDBITE
    0.55
     boyunca
    0.54
    Activations Density 0.274%

    No Known Activations