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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 14864
    Prev
    Next
    INDEX
    Explanations

    scientific terms and processes related to cellular analysis and protein quantification

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

    Text preceding citations/references

    np_acts-logits-general · gemini-2.0-flash

    Western blot and antibodies

    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
    +#+#
    -0.60
     yet
    -0.57
     still
    -0.50
    さえ
    -0.48
     maybe
    -0.47
     محفوظة
    -0.47
    áda
    -0.47
    ProgressHUD
    -0.46
     really
    -0.45
    PerformLayout
    -0.45
    POSITIVE LOGITS
     betweenstory
    0.79
     initComponents
    0.75
    SourceChecksum
    0.73
     nahilalakip
    0.69
     noDo
    0.68
     صوتيه
    0.68
     samples
    0.65
    ']):
    0.64
     AppColors
    0.64
    sonaro
    0.63
    Activations Density 1.258%

    No Known Activations