Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7349
    Prev
    Next
    INDEX
    Explanations

    professional references and credentials in real estate contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fabrik
    -0.60
    manufacturing
    -0.52
    matitis
    -0.50
    cipit
    -0.48
     Audiodateien
    -0.48
    ylvania
    -0.47
     وث
    -0.47
    HOTEL
    -0.47
     Presidencia
    -0.47
    rawan
    -0.47
    POSITIVE LOGITS
     agent
    1.36
     agents
    1.34
     Agent
    1.26
    Agent
    1.20
     Agents
    1.18
    agent
    1.15
     agente
    1.14
     realtor
    1.09
     AGENT
    1.08
    Agents
    1.07
    Activations Density 0.125%

    No Known Activations