© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7285
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to measurements and specifications in technical contexts

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

    technical symbols and notation in scientific or programming text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    󠁿
    -0.62
    \{\\
    -0.59
    󠁢
    -0.58
     dAtA
    -0.53
     zelve
    -0.53
     uLocal
    -0.52
     iconLine
    -0.52
     <<<<<<<<<<<<<<
    -0.52
     مشين
    -0.51
     jScrollPane
    -0.49
    POSITIVE LOGITS
     ویکی‌پدی
    0.59
    ----</
    0.51
    >//
    0.51
     nonUne
    0.47
     autorytatywna
    0.47
    oredCriteria
    0.46
    (){}
    0.45
    Thankyou
    0.43
    },[])
    0.43
    pushFollow
    0.43
    Activations Density 2.925%

    No Known Activations