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
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8641
    Prev
    Next
    INDEX
    Explanations

    elements related to storytelling, including plot development and character relationships in novels and adaptations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Show
    -0.30
     Performing
    -0.28
    URLException
    -0.28
    (@"%@",
    -0.26
    collection
    -0.25
    ContentAsync
    -0.24
     PERFORM
    -0.24
     представи
    -0.23
     verzame
    -0.23
    evos
    -0.22
    POSITIVE LOGITS
    IntoConstraints
    0.72
    Сюжет
    0.68
     zwiſchen
    0.64
     verſch
    0.63
    majánló
    0.60
     lyrics
    0.59
     beſch
    0.59
    mability
    0.58
     متعلقه
    0.58
    ᔢ
    0.57
    Activations Density 0.474%

    No Known Activations