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. 15544
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and phrases related to computational processing and electronic devices

    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
     صوتيه
    -0.38
    rrggbb
    -0.36
     Swallow
    -0.36
    MigrationBuilder
    -0.31
     swallow
    -0.28
     <<<<<<<<<<<<<<
    -0.28
    Pu
    -0.28
    ➯
    -0.28
    href
    -0.27
    óch
    -0.27
    POSITIVE LOGITS
    MethodManager
    0.88
    WaitGroup
    0.74
    Chham
    0.68
    SourceChecksum
    0.64
    ServletException
    0.62
    bootstrapcdn
    0.60
    /**
    0.60
    autaire
    0.59
     jsPsych
    0.58
    دانشنامهٔ
    0.58
    Activations Density 2.566%

    No Known Activations