© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 458
    Prev
    Next
    INDEX
    Explanations

    variable return values and retry indications in code

    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
    picasso
    -0.81
    jScrollPane
    -0.70
    KURZBESCHREIBUNG
    -0.66
     Plummer
    -0.64
    gonic
    -0.63
     /\.
    -0.63
     Chamberlain
    -0.62
     Sanderson
    -0.62
     halls
    -0.62
     PPS
    -0.61
    POSITIVE LOGITS
     ret
    2.77
     Ret
    2.76
    Ret
    2.68
    ret
    2.66
     RET
    2.13
    RET
    1.99
     Retina
    1.37
     Retreat
    1.36
     retra
    1.35
    rets
    1.30
    Activations Density 0.065%

    No Known Activations