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. 3763
    Prev
    Next
    INDEX
    Explanations

    instructions and conditions related to sample preparation and storage in a laboratory setting

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

    Stored at a specific temperature

    np_acts-logits-general · gemini-2.0-flash

    refrigerator and low temperatures

    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
     Berufs
    -0.51
    wol
    -0.49
     Siria
    -0.46
     slå
    -0.45
     Macau
    -0.44
     Fallon
    -0.43
    ǔ
    -0.43
     homotopy
    -0.43
     Jogo
    -0.42
    vietnam
    -0.42
    POSITIVE LOGITS
     refrigerator
    1.67
     fridge
    1.58
     refrigerated
    1.53
     freezer
    1.52
     refrigerate
    1.46
     refrigeration
    1.43
    refriger
    1.39
     Refrigerator
    1.37
     refrigerators
    1.35
    Refriger
    1.35
    Activations Density 0.213%

    No Known Activations