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. 3545
    Prev
    Next
    INDEX
    Explanations

    references to web addresses and XML-related attributes

    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
    NameInMap
    -0.56
    الإنجليزية
    -0.49
    amico
    -0.49
    errHandler
    -0.46
    RuleContext
    -0.45
    saraba
    -0.45
     doch
    -0.45
    ParallelGroup
    -0.44
    已有
    -0.44
     gehört
    -0.41
    POSITIVE LOGITS
    www
    1.06
    WWW
    0.90
    Www
    0.86
    Rohy
    0.78
    ();)
    0.78
     Audiodateien
    0.76
     WWW
    0.75
    onedDateTime
    0.75
    GHIJKLM
    0.74
    ExtendWith
    0.74
    Activations Density 0.067%

    No Known Activations