© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 29035
    Prev
    Next
    INDEX
    Explanations

    terms related to explosions and detonations

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

    explosion and detonation

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     Walkover
    -0.47
     alfombra
    -0.36
     kval
    -0.36
     difíciles
    -0.36
     kwal
    -0.35
     valiente
    -0.35
     compromisso
    -0.35
     cuerdas
    -0.34
     culturelle
    -0.34
     Normdatei
    -0.34
    POSITIVE LOGITS
     explosion
    0.75
     explosions
    0.75
     Administrativna
    0.71
     blast
    0.63
     explode
    0.59
    explosion
    0.59
     exploding
    0.59
     deton
    0.58
     Explosion
    0.57
     blow
    0.57
    Activations Density 0.093%

    No Known Activations