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. 4-GEMMASCOPE-RES-16K
    6. 3257
    Prev
    Next
    INDEX
    Explanations

    technical terms and structures related to statistical analysis and data processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.79
     typelib
    -0.68
     ویکی‌پدیا
    -0.67
    AndEndTag
    -0.63
    …~
    -0.59
     الاطلاع
    -0.58
     تكبرها
    -0.58
    hyrchwyd
    -0.57
    __(/*!
    -0.57
    niew
    -0.56
    POSITIVE LOGITS
    WriteLiteral
    0.53
    brtc
    0.52
    PyExc
    0.48
    ########.
    0.47
     Quanto
    0.47
     Sno
    0.47
     habl
    0.46
     թվական
    0.45
    buatan
    0.44
     ligiloj
    0.43
    Activations Density 1.100%

    No Known Activations