© 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. 3947
    Prev
    Next
    INDEX
    Explanations

    nouns and terms related to real estate transactions

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

    Real estate agents and sales

    np_acts-logits-general · gemini-2.0-flash

    real estate agents and realtors

    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
     Audiodateien
    -0.50
    ագրություններ
    -0.48
     gober
    -0.46
    iry
    -0.45
     Stiftung
    -0.43
    Hostel
    -0.43
     park
    -0.43
    ciles
    -0.42
     gelegen
    -0.42
    Manufactured
    -0.41
    POSITIVE LOGITS
     brokerage
    0.91
     agent
    0.90
     agents
    0.89
     Broker
    0.89
     AGENT
    0.82
    Broker
    0.81
     Realtor
    0.80
     salespeople
    0.80
    agent
    0.79
     Agent
    0.79
    Activations Density 0.144%

    No Known Activations