© 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. 2-GEMMASCOPE-RES-16K
    11. 3993
    Prev
    Next
    INDEX
    Explanations

    mathematical structures related to positive roots in polynomial or algebraic expressions

    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
    RenderAtEndOf
    -0.91
     avoient
    -0.88
     auroit
    -0.78
    SharedDtor
    -0.77
    AndEndTag
    -0.77
    httphttps
    -0.76
     quæ
    -0.76
     feroit
    -0.75
     purpoſe
    -0.75
    fjspx
    -0.75
    POSITIVE LOGITS
    Referanser
    0.60
    躇
    0.58
    ⇑
    0.55
     ویکی‌پدی
    0.53
    ngOnInit
    0.53
     '
    0.48
    rosophila
    0.48
    DebuggerNonUser
    0.47
    őbb
    0.46
    ↵
    0.45
    Activations Density 0.905%

    No Known Activations