© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3659
    Prev
    Next
    INDEX
    Explanations

    elements related to programming concepts and their applications

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

    text in Portuguese about programming concepts, particularly related to JavaScript and Node.js streaming and data processing.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered 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
    ambilan
    -0.39
    OVERR
    -0.39
    <unused60>
    -0.34
    <unused63>
    -0.34
     romántico
    -0.32
    évaluateur
    -0.32
     đ
    -0.32
    3
    -0.31
     lisäksi
    -0.31
    înd
    -0.30
    POSITIVE LOGITS
    MessageTagHelper
    0.77
     XNUMX
    0.76
     ſans
    0.70
    principalColumn
    0.67
    <unused43>
    0.66
    <unused28>
    0.66
    <pad>
    0.66
    <unused23>
    0.65
    <unused3>
    0.65
    [@BOS@]
    0.65
    Activations Density 0.060%

    No Known Activations