© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 1746
    Prev
    Next
    INDEX
    Explanations

    absence of significant content or information

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

    Text followed by colons

    np_acts-logits-general · gemini-2.0-flash

    evidence following list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    [];
    
    -0.51
     managing
    -0.46
    ological
    -0.46
     Public
    -0.45
     managed
    -0.45
    ®
    -0.44
     manages
    -0.44
     Mid
    -0.43
    tifying
    -0.43
    sisting
    -0.42
    POSITIVE LOGITS
     HasFactory
    0.97
    saraba
    0.91
    bootstrapcdn
    0.90
     kaarangay
    0.89
    InSection
    0.87
    featureID
    0.83
     '\\;'
    0.83
     religieuses
    0.82
    SpringRunner
    0.81
     estimés
    0.80
    Activations Density 0.294%

    No Known Activations