© 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. 4-GEMMASCOPE-RES-16K
    6. 15754
    Prev
    Next
    INDEX
    Explanations

    business-related terms and concepts that indicate profitability and market strategy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.59
    sidemargin
    -0.59
     kaarangay
    -0.58
     Normdatei
    -0.57
    usehen
    -0.56
    MemoryWarning
    -0.55
     pageContext
    -0.55
    EndContext
    -0.54
     CreateTagHelper
    -0.53
     linkovi
    -0.53
    POSITIVE LOGITS
     market
    0.65
     niches
    0.65
     profitable
    0.64
     niche
    0.63
     revenue
    0.62
     success
    0.61
     profitability
    0.61
     marke
    0.61
    market
    0.60
     successo
    0.58
    Activations Density 0.609%

    No Known Activations