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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9106
    Prev
    Next
    INDEX
    Explanations

    specific characters and events related to the Harry Potter series

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

    "Hog" or abbreviations, potentially in conversational text

    np_acts-logits-general · gemini-2.0-flash

    Harry Potter characters and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kegaard
    -0.38
    ğunu
    -0.38
     vå
    -0.36
     pekan
    -0.36
     Soldaten
    -0.35
    ggiata
    -0.35
    responseCode
    -0.35
     mengen
    -0.34
    łec
    -0.34
     Denne
    -0.34
    POSITIVE LOGITS
     Hogwarts
    0.65
    PyExc
    0.65
     AssemblyCulture
    0.58
    $_['
    0.57
    NgModule
    0.56
    patine
    0.56
     Rowling
    0.54
    ffindor
    0.54
     Dumbledore
    0.54
    aryen
    0.53
    Activations Density 0.119%

    No Known Activations