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. 11688
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to physical processes and models

    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
    wness
    -0.64
    IBarButtonItem
    -0.63
     Glan
    -0.58
    providedIn
    -0.56
     SPSS
    -0.55
    adple
    -0.55
    fahrens
    -0.54
    Compassion
    -0.53
     nakalista
    -0.53
     Tags
    -0.52
    POSITIVE LOGITS
     theory
    1.58
     theories
    1.44
    theory
    1.32
     Theory
    1.24
    Theory
    1.21
     explanation
    1.10
     Theories
    1.09
     THEORY
    1.09
     hypothesis
    1.08
    THEORY
    1.07
    Activations Density 1.013%

    No Known Activations