© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 13564
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases related to guidance or support

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

    infinitive verbs preceded by "to" (e.g., "to show", "to make", "to link", "to enable").

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Attempts
    -0.41
    poved
    -0.40
    writeFileSync
    -0.40
     riuscito
    -0.40
     Attempts
    -0.39
    verz
    -0.39
     endeav
    -0.39
    Attributed
    -0.38
     Allowed
    -0.38
     berusaha
    -0.37
    POSITIVE LOGITS
    ImageContext
    0.72
     ולה
    0.63
     pinulongan
    0.61
     oneself
    0.59
    Bronnen
    0.59
    AndEndTag
    0.58
    AddTagHelper
    0.58
     يتيمه
    0.56
    
    0.54
    ViewInit
    0.53
    Activations Density 1.005%

    No Known Activations