© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 9603
    Prev
    Next
    INDEX
    Explanations

    elements of storytelling and narrative structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.52
     חיצוניים
    -0.51
    Notae
    -0.47
     câte
    -0.45
    Ongoing
    -0.45
     Tite
    -0.45
    inā
    -0.44
    glich
    -0.43
     argint
    -0.43
    XmlAccessorType
    -0.43
    POSITIVE LOGITS
    findpost
    0.53
    addCriterion
    0.51
    RUnlock
    0.43
    LookAnd
    0.39
    enumii
    0.37
     while
    0.36
     simultaneously
    0.36
     again
    0.36
     paral
    0.35
     here
    0.35
    Activations Density 1.242%

    No Known Activations