© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 7807
    Prev
    Next
    INDEX
    Explanations

    the name "Bob" 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 @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CTC
    -0.72
     InputDecoration
    -0.72
    DebuggerNonUser
    -0.71
     VX
    -0.70
     SCE
    -0.69
     ITC
    -0.69
     PSM
    -0.68
    Aces
    -0.66
     Unwin
    -0.66
     DIA
    -0.66
    POSITIVE LOGITS
     Bob
    3.16
    Bob
    2.90
     bob
    2.66
    bob
    2.49
     BOB
    2.13
     bobs
    1.98
    BOB
    1.87
     Bobo
    1.30
     Boba
    1.16
     Robert
    1.03
    Activations Density 0.099%

    No Known Activations