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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12667
    Prev
    Next
    INDEX
    Explanations

    themes related to storytelling and personal reflection on experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dummy
    -0.45
    licherweise
    -0.44
     browse
    -0.42
     détach
    -0.41
    arschijnlijk
    -0.40
     arrivals
    -0.40
     miscellaneous
    -0.38
     manually
    -0.38
     Arrivals
    -0.37
     unavailable
    -0.37
    POSITIVE LOGITS
    AxisAlignment
    0.62
    KommentareTeilen
    0.59
    بوابة
    0.58
    Datuak
    0.57
    Portály
    0.57
    verwijspagina
    0.56
     Италијани
    0.54
    onAttach
    0.52
    Portail
    0.50
    IRQn
    0.50
    Activations Density 3.913%

    No Known Activations