© 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 106259
    Prev
    Next
    INDEX
    Explanations

    mentions of specific characters or names, particularly in a narrative or discussion context

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

    Username or name tokens used to directly address a person in IRC chats, emails, or formal communications, often followed by punctuation like a colon or comma.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     <=",
    -0.63
     autorytatywna
    -0.57
    InitVars
    -0.55
    +#+#
    -0.53
    StoreMessageInfo
    -0.50
    حياته
    -0.50
     otomatig
    -0.49
    oredCriteria
    -0.49
    BeginInit
    -0.48
     <<<<<<<<<<<<<<
    -0.47
    POSITIVE LOGITS
     please
    0.44
     ATTENTION
    0.37
    setContentView
    0.37
     dear
    0.37
     bienvenue
    0.36
     listeners
    0.35
    please
    0.34
     ơi
    0.34
     SqlCommand
    0.33
     Dear
    0.33
    Activations Density 0.062%

    No Known Activations