© 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. 7649
    Prev
    Next
    INDEX
    Explanations

    instances of numeric values or mathematical expressions

    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
     }</
    -0.52
    ><><
    -0.50
    +:+
    -0.50
     interloc
    -0.48
    mait
    -0.48
     Brood
    -0.48
     /></
    -0.47
    ocrat
    -0.47
    定向
    -0.47
    躇
    -0.46
    POSITIVE LOGITS
    9
    0.96
    AppMethodBeat
    0.52
     Administrativna
    0.45
    ers
    0.44
     pinulongan
    0.44
    Bronnen
    0.44
     שוליים
    0.42
    Климаты
    0.42
    8
    0.39
     nueve
    0.39
    Activations Density 1.014%

    No Known Activations