© 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. 33-GEMMASCOPE-RES-16K
    6. 145
    Prev
    Next
    INDEX
    Explanations

    concepts related to player motivation and capacity in gaming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnsafeEnabled
    -0.71
    msgTypes
    -0.69
     CreateTagHelper
    -0.63
    OGND
    -0.61
    RenderAtEndOf
    -0.59
    complexType
    -0.59
    Gweler
    -0.57
    Personensuche
    -0.56
    featureID
    -0.56
     biennial
    -0.56
    POSITIVE LOGITS
     someone
    0.60
     Someone
    0.57
    某个
    0.56
     either
    0.56
     somewhere
    0.52
     sesuatu
    0.51
    某种
    0.50
     determinada
    0.50
     alguien
    0.50
     someplace
    0.50
    Activations Density 1.575%

    No Known Activations