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. 11115
    Prev
    Next
    INDEX
    Explanations

    patterns of phrases related to retrieving or listing items, especially in programming contexts

    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
     "
    -0.68
    WireFormat
    -0.59
     lesquelles
    -0.55
     klikken
    -0.55
    ""
    -0.53
     ""));
    -0.53
    ')),
    -0.52
    ("")
    -0.52
    ')))
    -0.52
    に進
    -0.51
    POSITIVE LOGITS
    脚注の使い方
    1.34
     تضيفلها
    0.88
     يتيمه
    0.85
    principalColumn
    0.84
     ExecuteAsync
    0.81
    setDo
    0.75
    expandindo
    0.75
    AccessFile
    0.75
    ########.
    0.74
    DeleteBehavior
    0.73
    Activations Density 0.155%

    No Known Activations