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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 12649
    Prev
    Next
    INDEX
    Explanations

    terms related to specifications or speculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ::_('
    -1.07
    Personendaten
    -1.03
    sizeCache
    -1.00
     '\\;'
    -0.92
    fromCharCode
    -0.91
    HasAnnotation
    -0.90
    InputTagHelper
    -0.87
    niająca
    -0.86
     humanistic
    -0.86
    etheless
    -0.84
    POSITIVE LOGITS
     Spec
    1.98
     spec
    1.97
    spec
    1.91
    Spec
    1.87
    Spectrum
    1.67
     Spectrum
    1.66
     spectrum
    1.65
     SPEC
    1.65
     spectra
    1.64
    SPEC
    1.57
    Activations Density 0.113%

    No Known Activations