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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6873
    Prev
    Next
    INDEX
    Explanations

    sections of code or structured text related to programming or technical documentation

    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
     ſind
    -1.04
     ſei
    -0.96
    LookAnd
    -0.96
     كومونز
    -0.94
    出版年
    -0.93
    нгред
    -0.92
     queſta
    -0.91
     فريبيس
    -0.91
    richTextPanel
    -0.88
    ⟬
    -0.88
    POSITIVE LOGITS
    <eos>
    0.49
    .
    0.45
    The
    0.45
    ↵↵
    0.45
     the
    0.44
    2
    0.40
     
    0.38
    1
    0.38
    4
    0.37
    ,
    0.35
    Activations Density 0.635%

    No Known Activations