© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 9588
    Prev
    Next
    INDEX
    Explanations

    elements related to HTML coding and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    localctx
    -0.87
    StructEnd
    -0.76
    AccessorTable
    -0.75
    PerformLayout
    -0.73
    
    -0.73
    ColumnHeaders
    -0.71
     صوتيه
    -0.69
     متعلقه
    -0.68
    CodedInputStream
    -0.67
    OGND
    -0.67
    POSITIVE LOGITS
    __(/*!
    0.58
    ensed
    0.53
    vitis
    0.53
     débuts
    0.49
     charité
    0.49
    variance
    0.47
    География
    0.47
    dubbo
    0.47
     شناسی
    0.47
    derived
    0.46
    Activations Density 0.008%

    No Known Activations