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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 1913
    Prev
    Next
    INDEX
    Explanations

    scientific measurements or mathematical calculations related to ratios and estimates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Monta
    -0.44
    Mem
    -0.43
     centres
    -0.43
     centre
    -0.42
     bett
    -0.42
    jov
    -0.41
    ℕ
    -0.40
    bov
    -0.40
    cope
    -0.40
    нец
    -0.39
    POSITIVE LOGITS
     AssemblyCulture
    0.85
    findpost
    0.82
    enterOuterAlt
    0.81
    SourceChecksum
    0.79
     WaitForSeconds
    0.77
     незавершена
    0.68
     DialogInterface
    0.66
    ArrowToggle
    0.64
    ManagedBean
    0.64
    Filmographie
    0.63
    Activations Density 0.520%

    No Known Activations