© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 6030
    Prev
    Next
    INDEX
    Explanations

    concepts related to the abilities and characteristics of fictional creatures and their interactions with magic or enchantment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     newOwner
    -0.46
    DisplayMetrics
    -0.46
    IsMutable
    -0.46
     linkovi
    -0.40
     Савезне
    -0.40
    ніципалі
    -0.39
    السكان
    -0.38
     Kohlen
    -0.37
    ihnachten
    -0.36
     byteArray
    -0.36
    POSITIVE LOGITS
     AssemblyTitle
    0.66
     Resolve
    0.57
     rolls
    0.53
     roll
    0.52
    opposed
    0.51
     successes
    0.50
     dice
    0.50
     Advantage
    0.50
     Brawl
    0.49
     Spend
    0.49
    Activations Density 0.183%

    No Known Activations