Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 2235
    Prev
    Next
    INDEX
    Explanations

    JavaScript and programming language constructs related to functions and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     setColor
    -0.55
     setAddress
    -0.49
     الدع
    -0.47
    ->___
    -0.46
     blindness
    -0.46
     flamme
    -0.46
    localScale
    -0.45
    uro
    -0.45
    writeInt
    -0.44
    urman
    -0.44
    POSITIVE LOGITS
     get
    1.44
    get
    1.42
     GET
    1.28
     Get
    1.24
    Get
    1.18
    GET
    1.17
    AndGet
    1.13
     gotten
    1.09
     getting
    1.05
    gotten
    1.03
    Activations Density 0.050%

    No Known Activations