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. 19-GEMMASCOPE-RES-16K
    6. 2071
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OSSARY
    -0.53
     bon
    -0.47
    widetext
    -0.46
    </h2>
    -0.45
    )++;
    -0.45
     íntima
    -0.44
    kloped
    -0.43
    lieving
    -0.43
     való
    -0.43
    addContainerGap
    -0.43
    POSITIVE LOGITS
     indisponible
    0.74
     nakalista
    0.71
    transQ
    0.66
    Datuak
    0.66
    ########.
    0.64
    ConstraintMaker
    0.64
    VersionUID
    0.61
     "..\..\
    0.61
     EconPapers
    0.59
     betweenstory
    0.58
    Activations Density 0.241%

    No Known Activations