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. 20-GEMMASCOPE-RES-16K
    6. 1154
    Prev
    Next
    INDEX
    Explanations

    structural elements and attributes related to data representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    HTML list items

    np_acts-logits-general · gemini-2.0-flash

    HTML list items and data tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rosion
    -0.47
    ული
    -0.46
     mierda
    -0.45
     sobě
    -0.44
     Él
    -0.43
     ๆ
    -0.42
    спі
    -0.42
     <
    -0.41
    θεν
    -0.41
    resizingMask
    -0.41
    POSITIVE LOGITS
    onAttach
    0.83
     AssemblyCulture
    0.83
     nahilalakip
    0.78
     ddelweddau
    0.72
    DockStyle
    0.71
    AndEndTag
    0.71
    AndroidJUnit
    0.69
     CreateTagHelper
    0.68
    THISDAY
    0.67
    cstdio
    0.67
    Activations Density 0.391%

    No Known Activations