© 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. 9154
    Prev
    Next
    INDEX
    Explanations

    various types of identifiers and their associated attributes in data structures

    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
     مواليد
    -0.49
    enerated
    -0.48
     proportional
    -0.48
    SequentialGroup
    -0.47
    WriteBarrier
    -0.47
    šiu
    -0.46
    ')['
    -0.45
     Heer
    -0.45
    TryGetValue
    -0.44
     perci
    -0.44
    POSITIVE LOGITS
     виправивши
    0.91
    CodeAttribute
    0.77
     NSCoder
    0.68
     חיצוניים
    0.66
     يتيمه
    0.65
    NameInMap
    0.65
    ModelAdmin
    0.64
    EDEFAULT
    0.64
    uxxxx
    0.63
    enumi
    0.63
    Activations Density 0.211%

    No Known Activations