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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 12167
    Prev
    Next
    INDEX
    Explanations

    phrases that express uncertainty or questioning concerning existence or choice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding clauses

    np_acts-logits-general · gemini-2.0-flash

    pronouns that introduce conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ub
    -0.52
    cive
    -0.48
    ToFile
    -0.45
    mez
    -0.45
    rak
    -0.45
    mber
    -0.44
    Luc
    -0.43
     >
    -0.43
    MPEG
    -0.42
     ضمن
    -0.42
    POSITIVE LOGITS
     you
    0.99
     everyone
    0.86
     everybody
    0.83
     nobody
    0.82
     we
    0.81
    everyone
    0.77
    everybody
    0.76
     really
    0.76
     EVERYONE
    0.75
     chiunque
    0.75
    Activations Density 0.205%

    No Known Activations