© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 14202
    Prev
    Next
    INDEX
    Explanations

    statements regarding the rarity or uniqueness of specific medical conditions or phenomena

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

    infrequency or rareness

    np_acts-logits-general · gemini-2.0-flash

    rare or uncommon occurrences

    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
    BufferException
    -0.57
     <<<<<<<<<<<<<<
    -0.57
    AndEndTag
    -0.53
    Enllaces
    -0.52
    ModelForm
    -0.50
    клопе
    -0.50
     ')[
    -0.50
    তথ্যসূত্র
    -0.49
    DESCRIPTOR
    -0.49
    AutoScaleMode
    -0.48
    POSITIVE LOGITS
     rare
    2.84
     rarity
    2.53
    Rare
    2.45
    rare
    2.44
     rarer
    2.37
     Rare
    2.33
     rarest
    2.21
     uncommon
    2.15
     rarely
    2.15
     RARE
    2.13
    Activations Density 0.559%

    No Known Activations