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. 13-GEMMASCOPE-RES-16K
    6. 33
    Prev
    Next
    INDEX
    Explanations

    conditional statements and checks related to boolean values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    logical values or conditions, such as true/false or yes/no, often in the context of decision-making or configuration settings.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     linkovi
    -0.53
    BibitemShut
    -0.52
    agaimana
    -0.52
    ()?;
    -0.51
     כלל
    -0.50
     Pera
    -0.50
     lắm
    -0.50
    Heya
    -0.50
    Hubert
    -0.50
     Gracia
    -0.49
    POSITIVE LOGITS
    ConstraintMaker
    0.76
    >{@
    0.74
    CodeAttribute
    0.72
    complexContent
    0.70
    aarrggbb
    0.66
    AsUp
    0.64
    DockStyle
    0.63
    GOTREF
    0.63
     estekak
    0.62
    GeneratedMessage
    0.61
    Activations Density 0.531%

    No Known Activations