© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 8291
    Prev
    Next
    INDEX
    Explanations

    automotive parts and specifications

    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
    脚注の使い方
    -0.60
    yship
    -0.58
    ˏ
    -0.52
    tty
    -0.49
    ynthesis
    -0.48
    #+#
    -0.48
    getline
    -0.45
    permalink
    -0.45
    Referencer
    -0.43
     jsonify
    -0.43
    POSITIVE LOGITS
    MockBean
    0.69
    Filmographie
    0.66
    IsMutable
    0.65
     Wikimedijinoj
    0.64
    AccessorTable
    0.62
    Hentet
    0.61
    Obrázky
    0.59
    StoryboardSegue
    0.58
     Pristupljeno
    0.56
    jfree
    0.55
    Activations Density 0.424%

    No Known Activations