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. 4-GEMMASCOPE-RES-16K
    6. 3540
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pina
    -0.51
     Wydawnictwo
    -0.49
    imageshack
    -0.49
     Shoemaker
    -0.48
    ESD
    -0.47
     Jost
    -0.47
    ode
    -0.46
    sidemargin
    -0.46
     strength
    -0.46
     train
    -0.45
    POSITIVE LOGITS
    parsedMessage
    0.83
     allAfrica
    0.75
    例句
    0.73
    newArrayList
    0.71
    rungsseite
    0.66
     OnInit
    0.64
    ArrowToggle
    0.64
    AddTagHelper
    0.63
     beginnetje
    0.62
    clusal
    0.61
    Activations Density 0.923%

    No Known Activations