© 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. 5-GEMMASCOPE-RES-16K
    11. 6782
    Prev
    Next
    INDEX
    Explanations

    terms related to searching for or obtaining information or resources

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

    recurring instances of the word "find."

    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
     ProtoMessage
    -0.76
    versation
    -0.69
     Cowley
    -0.68
     Astor
    -0.67
    uerung
    -0.67
    vereignty
    -0.66
    ניתן
    -0.65
     Cæsar
    -0.64
     sanitarias
    -0.64
    UserScript
    -0.64
    POSITIVE LOGITS
     FIND
    1.85
    FIND
    1.79
    find
    1.70
    Find
    1.70
     Find
    1.63
     find
    1.59
     finds
    1.58
     Finds
    1.52
     Findlay
    1.48
     finding
    1.36
    Activations Density 0.076%

    No Known Activations