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. 15814
    Prev
    Next
    INDEX
    Explanations

    titles and roles related to legal and governmental positions

    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
    tituzione
    -0.53
     givet
    -0.45
    Says
    -0.45
    שר
    -0.44
     andet
    -0.44
     famiglie
    -0.43
    ola
    -0.42
    Rem
    -0.42
     egentlig
    -0.42
    ⓘ
    -0.42
    POSITIVE LOGITS
    TargetException
    1.04
    MethodManager
    0.80
    sizeCache
    0.79
     Efq
    0.79
     purpoſe
    0.76
    PyExc
    0.75
    twimg
    0.74
    webElementXpaths
    0.72
    culable
    0.72
    PerformLayout
    0.72
    Activations Density 0.089%

    No Known Activations