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. 4-GEMMASCOPE-RES-16K
    6. 819
    Prev
    Next
    INDEX
    Explanations

    references to JavaScript libraries and associated code elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vectorielle
    -0.73
    TagMode
    -0.72
    endphp
    -0.71
    nastics
    -0.69
     useDispatch
    -0.68
     sanitarias
    -0.66
    entuh
    -0.65
    nessed
    -0.65
     Mémoires
    -0.64
     Treue
    -0.64
    POSITIVE LOGITS
    ########.
    0.75
     OFDb
    0.65
    #+#
    0.58
    abestanden
    0.54
     ')[
    0.42
     betweenstory
    0.42
    fod
    0.42
    getInteger
    0.41
    transQ
    0.41
    (&_
    0.41
    Activations Density 4.877%

    No Known Activations