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. 24-GEMMASCOPE-RES-16K
    6. 2332
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and queries related to statistics and linear algebra

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

    Follows "from", "in", or open parenthesis in mathematical or exercise contexts

    np_acts-logits-general · gemini-2.0-flash

    exercise or problem wording

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.57
     censiti
    -0.55
     Normdatei
    -0.52
    kloped
    -0.49
    AsUp
    -0.48
    DotNetBar
    -0.47
    obald
    -0.45
    affordable
    -0.45
    UnsafeEnabled
    -0.44
     protoimpl
    -0.43
    POSITIVE LOGITS
     Exercise
    1.16
     Problem
    1.12
     Exercises
    1.10
     Problems
    1.04
    Problem
    1.04
     exercises
    1.04
     exercise
    1.03
     problem
    1.01
    Exercise
    0.99
    Exercises
    0.96
    Activations Density 0.392%

    No Known Activations