Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-GEMMASCOPE-RES-16K
    6. 1777
    Prev
    Next
    INDEX
    Explanations

    LaTeX package references in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    گز
    -0.50
    ntable
    -0.50
    AutoScaleMode
    -0.46
     cast
    -0.45
     rec
    -0.45
     In
    -0.44
    schild
    -0.42
     Briggs
    -0.41
    eva
    -0.41
     Zwie
    -0.41
    POSITIVE LOGITS
    tagHelper
    1.78
    ScopeManager
    1.59
    gms
    1.47
    tagHelperRunner
    1.28
     useEffect
    1.26
    useEffect
    1.23
    jspx
    1.18
    BeginInit
    1.12
    ⓧ
    1.07
    ngOnInit
    1.05
    Activations Density 0.013%

    No Known Activations