© 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. 14-GEMMASCOPE-RES-16K
    11. 9848
    Prev
    Next
    INDEX
    Explanations

    instances of string literals, particularly with specific quote and delimiter characters in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.89
    djangoproject
    -0.75
    SequentialGroup
    -0.75
    RepeatedField
    -0.67
     po
    -0.67
     AssemblyCulture
    -0.66
    nocache
    -0.62
    ↵
    -0.60
    [toxicity=0]
    -0.60
    EndContext
    -0.58
    POSITIVE LOGITS
     pleaſure
    1.25
     raiſ
    1.20
     juſt
    1.12
    !("{
    1.08
     purpoſe
    1.08
     faſt
    1.07
     ſen
    1.07
     Anſ
    1.05
     Inſ
    1.02
     myſelf
    1.02
    Activations Density 0.124%

    No Known Activations