© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 95451
    Prev
    Next
    INDEX
    Explanations

    symbols and formatting elements typically found in mathematical expressions or equations

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

    closing punctuation followed by words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    хозяй
    -0.37
    StackNavigator
    -0.34
     createSlice
    -0.33
    SequentialGroup
    -0.31
    PlayerPrefs
    -0.29
    Bukkit
    -0.28
    何
    -0.28
    listView
    -0.28
     Tour
    -0.27
    LIV
    -0.27
    POSITIVE LOGITS
    AddTagHelper
    0.80
     autorytatywna
    0.61
     nahilalakip
    0.61
    <?
    0.60
    LEncoder
    0.60
    Diweddarwch
    0.59
    XmlAccessType
    0.58
     înc
    0.57
     vandens
    0.55
    tagHelperRunner
    0.55
    Activations Density 0.027%

    No Known Activations