© 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. 10-GEMMASCOPE-RES-16K
    11. 3313
    Prev
    Next
    INDEX
    Explanations

    HTML document structure elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     šte
    -0.54
     (
    -0.54
    ระ
    -0.53
    ...
    -0.49
    ră
    -0.49
    lal
    -0.47
    houden
    -0.47
    ce
    -0.47
    er
    -0.46
    S
    -0.46
    POSITIVE LOGITS
    MemoryWarning
    1.28
    SourceChecksum
    1.14
     ExecuteAsync
    1.11
    principalTable
    1.09
     resourceCulture
    1.08
     viewDidLoad
    1.08
    KURZBESCHREIBUNG
    1.08
    onViewCreated
    1.08
    SequentialGroup
    1.05
     viewType
    1.04
    Activations Density 0.041%

    No Known Activations