© 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. 31-GEMMASCOPE-RES-131K
    6. 44003
    Prev
    Next
    INDEX
    Explanations

    elements of code or markup language, particularly focusing on formatting and structure

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

    code and content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     queſta
    -0.98
     utafitiHapana
    -0.98
    SequentialGroup
    -0.96
     يتيمه
    -0.93
     CreateTagHelper
    -0.91
    Diweddarwch
    -0.86
     pinulongan
    -0.85
    Tikang
    -0.84
     ब्रेकडाउन
    -0.81
    ConstraintMaker
    -0.81
    POSITIVE LOGITS
     text
    0.51
     article
    0.46
     fragment
    0.40
     texts
    0.38
    Text
    0.37
     textes
    0.34
    Description
    0.33
     texte
    0.33
     Text
    0.31
     document
    0.30
    Activations Density 0.011%

    No Known Activations