© 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. 14-GEMMASCOPE-RES-16K
    11. 12758
    Prev
    Next
    INDEX
    Explanations

    numeric representations and sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikimedijinoj
    -1.05
    complexContent
    -0.93
     linkovi
    -0.92
    audiovisuel
    -0.92
    AutoresizingMask
    -0.91
    Geplaatst
    -0.91
     '\\;'
    -0.90
    曖昧さ回避
    -0.89
    InputBorder
    -0.87
    EndGlobalSection
    -0.87
    POSITIVE LOGITS
    ↵↵
    0.76
     
    0.67
    ↵
    0.60
     $
    0.59
     P
    0.54
    </h4>
    0.51
    </h2>
    0.49
     I
    0.48
     la
    0.47
    </blockquote>
    0.46
    Activations Density 7.716%

    No Known Activations