© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10703
    Prev
    Next
    INDEX
    Explanations

    phrases related to political critiques and unethical behavior

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

    Word followed by an adjective

    np_acts-logits-general · gemini-2.0-flash

    should surely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Richtlinien
    -0.45
     definately
    -0.41
    ContextCompat
    -0.41
     palha
    -0.40
     permasalahan
    -0.40
    ungkinan
    -0.39
     situaciones
    -0.39
     "...
    -0.39
     digress
    -0.39
     influenci
    -0.38
    POSITIVE LOGITS
    CppMethod
    0.61
     HasFactory
    0.60
    Personendaten
    0.59
     animating
    0.57
     CURIAM
    0.56
     autorytatywna
    0.56
     bArr
    0.56
    hyrchwyd
    0.56
     interlocutor
    0.56
    parsedMessage
    0.55
    Activations Density 1.588%

    No Known Activations