© 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. 1482
    Prev
    Next
    INDEX
    Explanations

    proper names and identifiers in various contexts, such as legal cases and scientific data

    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
     Conley
    -0.52
     Hales
    -0.49
     Glaser
    -0.44
     Farley
    -0.42
     Pineda
    -0.42
    AuthContext
    -0.40
     Wale
    -0.39
     Spicer
    -0.39
     Balkon
    -0.39
     Holman
    -0.39
    POSITIVE LOGITS
     CMM
    0.86
     EDD
    0.84
     ECC
    0.82
     MPP
    0.82
     ABB
    0.78
     OPP
    0.78
     ICC
    0.77
    OPP
    0.77
    AMM
    0.76
     IFF
    0.75
    Activations Density 2.502%

    No Known Activations