© 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. 19-GEMMASCOPE-RES-16K
    11. 1670
    Prev
    Next
    INDEX
    Explanations

    semicolon and curly brace characters used to signify the end of statements and blocks in programming code

    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
     Efq
    -0.83
     ―――――
    -0.68
     myſelf
    -0.67
    ſelf
    -0.66
    OGND
    -0.65
    IsPostBack
    -0.64
     AssemblyTitle
    -0.62
     Loa
    -0.61
     elif
    -0.61
     Jefus
    -0.60
    POSITIVE LOGITS
    memoized
    0.59
    <eos>
    0.58
    Varint
    0.56
    basicConfig
    0.52
     manusia
    0.48
     فريبيس
    0.48
    ...@
    0.46
    twimg
    0.45
     thus
    0.44
    return
    0.44
    Activations Density 0.060%

    No Known Activations