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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 18-GEMMASCOPE-RES-16K
    6. 8654
    Prev
    Next
    INDEX
    Explanations

    information related to mold growth and its environmental conditions

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

    air circulation or ventilation

    np_acts-logits-general · gemini-2.0-flash

    ventilation

    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
    mobileqq
    -0.64
     ProtoMessage
    -0.63
    期刊论文
    -0.59
    Jeografia
    -0.58
     réve
    -0.57
    toThrow
    -0.54
     skjø
    -0.54
    etna
    -0.54
    IUrlHelper
    -0.54
     Administrativna
    -0.53
    POSITIVE LOGITS
     ventilation
    1.69
     venti
    1.35
     Ventilation
    1.33
    ventilation
    1.26
     ventilated
    1.23
     airflow
    1.22
    Ventilation
    1.21
     венти
    1.11
     air
    1.11
     cooling
    1.10
    Activations Density 0.194%

    No Known Activations