© 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. 5-GEMMASCOPE-RES-16K
    6. 10764
    Prev
    Next
    INDEX
    Explanations

    the word "based" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ginn
    -0.74
     gug
    -0.73
     Scu
    -0.72
     Winfrey
    -0.70
     textView
    -0.70
    Scu
    -0.69
     displacement
    -0.69
     Gummi
    -0.68
     Schwan
    -0.68
     Greenwich
    -0.68
    POSITIVE LOGITS
     based
    1.99
     Based
    1.96
    Based
    1.92
    based
    1.84
     BASED
    1.84
    BASED
    1.83
     basé
    1.63
     basée
    1.52
     basado
    1.46
     basados
    1.35
    Activations Density 0.094%

    No Known Activations