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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 68925
    Prev
    Next
    INDEX
    Explanations

    names or references to individuals and their contributions or achievements

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

    names and pronouns followed by actions

    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
     فريبيس
    -0.62
     CreateTagHelper
    -0.59
    Чыгана
    -0.52
    paravant
    -0.52
    HasForeignKey
    -0.50
    undrum
    -0.49
    crapers
    -0.49
     autorytatywna
    -0.48
    theless
    -0.46
     censiti
    -0.46
    POSITIVE LOGITS
    #+#
    0.45
    +#+
    0.45
    StackNavigator
    0.43
     strength
    0.39
    contentLoaded
    0.39
     working
    0.39
     pioneers
    0.38
     [*]
    0.36
    Carriera
    0.36
     guided
    0.34
    Activations Density 0.029%

    No Known Activations