© 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. 11873
    Prev
    Next
    INDEX
    Explanations

    the presence of delimiters or special formatting characters often used in programming or mathematical expressions

    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
    ValueStyle
    -0.83
     gratuites
    -0.82
     religieuses
    -0.81
     vectorielles
    -0.80
     AssemblyVersion
    -0.79
     extérieures
    -0.77
     supérieurs
    -0.76
     vertes
    -0.75
     actuelles
    -0.75
     gratuits
    -0.74
    POSITIVE LOGITS
     Sist
    0.58
    De
    0.57
     de
    0.49
    _
    0.46
     pled
    0.46
    URBANA
    0.44
     generals
    0.44
     juries
    0.44
     Exter
    0.43
    fis
    0.43
    Activations Density 0.063%

    No Known Activations