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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 9393
    Prev
    Next
    INDEX
    Explanations

    programming functions and their components

    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
     newState
    -0.35
     supplies
    -0.34
     bun
    -0.33
     community
    -0.33
     Self
    -0.33
     do
    -0.33
     tiss
    -0.33
     favourable
    -0.32
     Environment
    -0.32
     Supplies
    -0.32
    POSITIVE LOGITS
     يتيمه
    0.74
     CreateTagHelper
    0.64
     propOrder
    0.62
    ⤹
    0.62
     Roskov
    0.62
    NameInMap
    0.60
    MLLoader
    0.60
     незавершена
    0.60
    ConstraintMaker
    0.57
     ProtoMessage
    0.56
    Activations Density 0.204%

    No Known Activations