© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1282
    Prev
    Next
    INDEX
    Explanations

    references to specific organizations and their roles or activities

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

    Legal entities and company names

    np_acts-logits-general · gemini-2.0-flash

    company names and 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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    UnusedPrivate
    -0.42
     ControllerBase
    -0.35
     federal
    -0.35
    stdc
    -0.34
     necessarily
    -0.33
     PropertyChanged
    -0.33
     difficult
    -0.32
    ADELPHIA
    -0.31
     government
    -0.31
     AppCompat
    -0.29
    POSITIVE LOGITS
     LLC
    0.71
     Ltd
    0.67
     Efq
    0.65
    Ltd
    0.60
     llc
    0.58
     vœ
    0.57
     становника
    0.57
     Inc
    0.56
     hosting
    0.56
    ngdoc
    0.56
    Activations Density 0.412%

    No Known Activations