© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8283
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to positive affirmations and support

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

    Preceding specific nouns

    np_acts-logits-general · gemini-2.0-flash

    outstanding heroism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     elettrico
    -0.49
     jambes
    -0.46
    りますが
    -0.45
     barnen
    -0.44
     connues
    -0.43
     hacerte
    -0.43
    HttpPut
    -0.43
     المعيارى
    -0.43
     banques
    -0.43
     obyvateľov
    -0.42
    POSITIVE LOGITS
     things
    0.93
     way
    0.89
     ways
    0.81
     kinds
    0.79
     amount
    0.78
     havoc
    0.76
     kind
    0.75
     CreateTagHelper
    0.74
     places
    0.73
     decisions
    0.72
    Activations Density 0.438%

    No Known Activations