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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 14541
    Prev
    Next
    INDEX
    Explanations

    terms related to the processes involved in tissue embedding and histology

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

    Embedding in paraffin/silicone molds

    np_acts-logits-general · gemini-2.0-flash

    molds and casting

    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
    WithIOException
    -0.60
    
    -0.59
     CreateTagHelper
    -0.58
    XmlRootElement
    -0.58
    ContentAsync
    -0.57
    ⓧ
    -0.56
    verifyException
    -0.54
    opsida
    -0.51
    owatt
    -0.51
     protoimpl
    -0.51
    POSITIVE LOGITS
     mold
    1.24
     mould
    1.20
     molds
    1.20
     moulds
    1.14
     Mould
    1.08
     molde
    1.06
    mold
    1.02
     Mold
    1.02
     molding
    1.00
    Mold
    0.99
    Activations Density 0.356%

    No Known Activations