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-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8425
    Prev
    Next
    INDEX
    Explanations

    instances of the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rest
    -0.45
    est
    -0.39
     hari
    -0.38
     vs
    -0.38
    dd
    -0.38
     or
    -0.37
    bod
    -0.37
    ć
    -0.37
    ্ন
    -0.37
     and
    -0.36
    POSITIVE LOGITS
    AddTagHelper
    0.98
    IContainer
    0.96
     betweenstory
    0.95
    脚注の使い方
    0.90
    AutoScaleMode
    0.88
     BoxFit
    0.85
    enumi
    0.84
    UseVisualStyle
    0.84
     myſelf
    0.84
     crdi
    0.82
    Activations Density 0.304%

    No Known Activations