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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 6959
    Prev
    Next
    INDEX
    Explanations

    references to the term "magazine" and related variations

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

    "Mag" or "Magazine" and variants

    np_acts-logits-general · gemini-2.0-flash

    mag words

    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-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
     Trav
    -0.54
     Atlantis
    -0.54
    adaptiveStyles
    -0.53
     Toussaint
    -0.49
     rami
    -0.48
     atlan
    -0.48
     rowCount
    -0.48
     Calais
    -0.47
     porto
    -0.47
    trie
    -0.47
    POSITIVE LOGITS
    Mag
    1.58
     Mag
    1.53
     mag
    1.46
    MAG
    1.42
     MAG
    1.40
    mag
    1.38
     Maguire
    1.13
     Magazine
    1.12
     magazine
    1.11
     mags
    1.09
    Activations Density 0.270%

    No Known Activations