© 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. 18-GEMMASCOPE-RES-16K
    11. 6422
    Prev
    Next
    INDEX
    Explanations

    instances of conjunctions and phrases indicating continuity or connection

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

    Follows "and," "genes," "January," or "were"

    np_acts-logits-general · gemini-2.0-flash

    future or suggestions

    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
    IUrlHelper
    -0.91
     فريبيس
    -0.87
    Personendaten
    -0.84
    AndEndTag
    -0.83
     resourceCulture
    -0.82
    évaluateur
    -0.77
    sidemargin
    -0.76
    InvalidProtocol
    -0.76
    featureID
    -0.74
    
    -0.72
    POSITIVE LOGITS
     البته
    0.61
     futuras
    0.55
     future
    0.54
     suggestions
    0.51
     explanation
    0.48
     futura
    0.47
    ましい
    0.47
     mulig
    0.47
     apologies
    0.46
     confirmed
    0.46
    Activations Density 0.320%

    No Known Activations