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. 5-GEMMASCOPE-RES-16K
    6. 8639
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditions or requirements for achieving certain goals or actions

    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
    vedi
    -0.67
    tableFuture
    -0.63
    pantalón
    -0.57
    obald
    -0.56
    unnitel
    -0.56
    orcid
    -0.55
     Arabian
    -0.55
     lettres
    -0.53
     Juden
    -0.50
     idée
    -0.49
    POSITIVE LOGITS
    MigrationBuilder
    0.67
     transfieras
    0.64
    intios
    0.64
    PickerController
    0.62
    httphttps
    0.59
     nhiêu
    0.57
    )}-
    0.57
    \{\\
    0.57
     désolés
    0.56
    новништво
    0.55
    Activations Density 0.158%

    No Known Activations