Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6231
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to political processes and electoral dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.47
     Gesicht
    -0.44
     Schuhe
    -0.41
     Erscheinung
    -0.40
     disambiguazione
    -0.39
     Füßen
    -0.39
     Geburtstag
    -0.37
     muere
    -0.37
     navideños
    -0.36
     gynhyrchwyd
    -0.36
    POSITIVE LOGITS
    bootstrapcdn
    0.65
    CloseOperation
    0.52
     government
    0.50
     Infórmanos
    0.50
     gover
    0.50
     electing
    0.50
    bcryptjs
    0.49
     Govern
    0.48
    rusted
    0.48
    ContentLoaded
    0.48
    Activations Density 0.446%

    No Known Activations