© 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. 9485
    Prev
    Next
    INDEX
    Explanations

    questions and requests for information

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

    Following "Let" in math problems

    np_acts-logits-general · gemini-2.0-flash

    mathematical answers

    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
    colnshire
    -0.45
    __":
    -0.44
    reszcie
    -0.44
    Easier
    -0.42
    ρους
    -0.41
    هة
    -0.41
    ’,
    -0.40
    __':
    -0.40
    ()',
    -0.40
     batte
    -0.39
    POSITIVE LOGITS
    answer
    1.15
     answer
    1.13
    Explanation
    0.98
    Autoritní
    0.96
     Answer
    0.94
    brainly
    0.93
     ANSWER
    0.90
     answered
    0.87
    ANSWER
    0.86
     answers
    0.85
    Activations Density 0.903%

    No Known Activations