© 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. 22-GEMMASCOPE-RES-16K
    11. 1459
    Prev
    Next
    INDEX
    Explanations

    conditional statements or phrases that denote hypothetical situations

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

    "If" followed by a pronoun or "anything"

    np_acts-logits-general · gemini-2.0-flash

    conditional statements starting with if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ―――――
    -0.62
    parsedMessage
    -0.61
    herself
    -0.58
     ་་
    -0.55
     whiche
    -0.54
    ՚
    -0.53
    them
    -0.53
     RSSSF
    -0.53
    selves
    -0.52
     herself
    -0.50
    POSITIVE LOGITS
     you
    1.30
     they
    1.19
     we
    1.19
     anyone
    1.19
     anything
    1.12
     indeed
    1.10
     ever
    1.01
     anybody
    1.01
     someone
    0.96
     there
    0.95
    Activations Density 0.174%

    No Known Activations