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. 7-GEMMASCOPE-RES-16K
    6. 9112
    Prev
    Next
    INDEX
    Explanations

    biorelevant terms and identifiers related to scientific concepts and studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -1.35
     AssemblyCulture
    -1.02
    存于互联网档案馆
    -1.01
     tartalomajánló
    -0.96
    rungsseite
    -0.94
     مرئيه
    -0.90
    omitempty
    -0.88
    yntaxException
    -0.86
    //
    -0.81
    DockStyle
    -0.80
    POSITIVE LOGITS
    ny
    0.61
    lot
    0.57
    key
    0.54
    </i>
    0.52
    lik
    0.51
     notare
    0.50
    q
    0.50
    ora
    0.49
    original
    0.49
    any
    0.49
    Activations Density 2.248%

    No Known Activations