© 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. 9363
    Prev
    Next
    INDEX
    Explanations

    syntax and constructs related to programming functions and processes

    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
    RefNanny
    -0.42
     STANFORD
    -0.37
     Seychelles
    -0.33
    .*")]
    -0.32
     Stearns
    -0.32
    ainville
    -0.32
     Mauri
    -0.31
     Mombasa
    -0.31
     Chilean
    -0.30
    vu
    -0.30
    POSITIVE LOGITS
     Oklahoma
    1.09
    Oklahoma
    1.02
     Okla
    0.92
     Tulsa
    0.84
    LAHOMA
    0.81
    lahoma
    0.71
     OK
    0.68
     Ok
    0.61
     ok
    0.60
     arşivlendi
    0.57
    Activations Density 0.241%

    No Known Activations