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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 14038
    Prev
    Next
    INDEX
    Explanations

    references to social justice issues and systemic inequalities

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

    following coordinating conjunctions

    np_acts-logits-general · gemini-2.0-flash

    compound subjects or predicates

    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
     r
    -1.08
     R
    -1.07
    R
    -1.03
     RR
    -0.99
     Rhi
    -0.98
     RS
    -0.97
     RP
    -0.97
     RA
    -0.95
     RB
    -0.93
    getR
    -0.93
    POSITIVE LOGITS
    łasz
    0.31
    CompleteListener
    0.31
    enterOuterAlt
    0.30
    lgari
    0.29
     SafeMath
    0.29
    lagu
    0.29
    llingwood
    0.29
     assurent
    0.28
    ास्त
    0.28
     Gunter
    0.28
    Activations Density 1.764%

    No Known Activations