© 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. 27-GEMMASCOPE-RES-16K
    6. 9231
    Prev
    Next
    INDEX
    Explanations

    patterns of mathematical or statistical notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nonUne
    -0.77
     lenker
    -0.71
    Portail
    -0.69
     ſind
    -0.68
     uLocal
    -0.67
    IUrlHelper
    -0.65
     utafitiHapana
    -0.60
     ſei
    -0.60
    ]")]
    -0.58
     Erişim
    -0.58
    POSITIVE LOGITS
    enumi
    0.77
    enumii
    0.45
    }{
    0.43
     certificación
    0.40
     supérieurs
    0.38
     dictadura
    0.37
     supérieures
    0.36
     deportiva
    0.36
     jälkeen
    0.35
     abstrato
    0.34
    Activations Density 0.012%

    No Known Activations