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 - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 88949
    Prev
    Next
    INDEX
    Explanations

    references to the song "Hallelujah" and the location "Randolph."

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

    Halle, Brandenburg, Randolph

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    illow
    -0.32
     outlines
    -0.31
     informs
    -0.29
     thiện
    -0.28
     inform
    -0.27
    abs
    -0.25
    (
    -0.25
    -\
    -0.25
    ◼
    -0.25
    (\
    -0.25
    POSITIVE LOGITS
     Halle
    1.71
    Halle
    1.66
     halle
    1.15
    halle
    1.02
    enciaga
    0.93
     Randolph
    0.88
     Brandenburg
    0.85
    lujah
    0.85
    bouncycastle
    0.79
    contentLoaded
    0.73
    Activations Density 0.004%

    No Known Activations