© 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. 24-GEMMASCOPE-RES-16K
    11. 12557
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and inequalities

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

    Mathematical expressions and rearrangements

    np_acts-logits-general · gemini-2.0-flash

    rearranging and factoring mathematical expressions

    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
    AsUp
    -0.76
    KURZBESCHREIBUNG
    -0.67
     saites
    -0.59
    رشف
    -0.59
    Trama
    -0.57
    ensin
    -0.56
    GEBURTSDATUM
    -0.56
     CreateTagHelper
    -0.53
    ఔ
    -0.52
    عداد
    -0.52
    POSITIVE LOGITS
     rearrange
    0.67
     rewriting
    0.66
     factoring
    0.66
     שוליים
    0.63
     rewrite
    0.63
     rearrangement
    0.63
     Rear
    0.60
    fact
    0.58
     rearranging
    0.58
     Isol
    0.57
    Activations Density 1.038%

    No Known Activations