© 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-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 16271
    Prev
    Next
    INDEX
    Explanations

    expressions of apology or admission of fault

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arschijnlijk
    -0.85
     probab
    -0.83
     Houd
    -0.82
     pinulongan
    -0.74
     wund
    -0.72
    UnsafeEnabled
    -0.70
    mschrijving
    -0.69
     Saad
    -0.69
    xions
    -0.67
     prés
    -0.66
    POSITIVE LOGITS
     definitely
    0.91
     lenker
    0.84
    Definitely
    0.83
    definitely
    0.82
     AssemblyVersion
    0.81
     Definitely
    0.79
     otomatig
    0.68
     McIn
    0.66
    sterious
    0.64
    =}
    0.63
    Activations Density 0.031%

    No Known Activations