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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 6066
    Prev
    Next
    INDEX
    Explanations

    references to classes and hierarchical structures in programming or chemistry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.83
    AndEndTag
    -0.76
     AssemblyTitle
    -0.70
    SharedCtor
    -0.67
    NameInMap
    -0.66
    🏿
    -0.65
    🏽
    -0.63
    webElementXpaths
    -0.61
    ▾
    -0.61
    familien
    -0.61
    POSITIVE LOGITS
    rooms
    0.94
    ically
    0.92
    ROOM
    0.71
    ics
    0.70
    sieke
    0.69
    DriverManager
    0.67
    mates
    0.67
    CastException
    0.66
    mate
    0.65
    ica
    0.62
    Activations Density 0.138%

    No Known Activations