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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14919
    Prev
    Next
    INDEX
    Explanations

    coding terminology and function calls related to graphical user interfaces and data manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.87
    MigrationBuilder
    -0.75
     Chwiliwch
    -0.73
    SequentialGroup
    -0.71
    Diweddarwch
    -0.68
    AnchorStyles
    -0.57
    ValueGeneration
    -0.57
    DockStyle
    -0.56
    MessageTagHelper
    -0.55
    رشف
    -0.54
    POSITIVE LOGITS
     Program
    0.40
     hab
    0.39
     emm
    0.38
     Loy
    0.38
     loy
    0.38
    linearGradient
    0.37
     lom
    0.37
     signature
    0.36
    borderTop
    0.36
     header
    0.36
    Activations Density 0.642%

    No Known Activations