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. 7-GEMMASCOPE-RES-16K
    6. 6105
    Prev
    Next
    INDEX
    Explanations

    discourse markers that indicate contrast or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.63
     Spice
    -0.57
    خت
    -0.57
     صوتيه
    -0.56
    UnsafeEnabled
    -0.55
    DockStyle
    -0.55
     Flesh
    -0.54
     updateUser
    -0.54
    TagMode
    -0.53
    олові
    -0.52
    POSITIVE LOGITS
    مصادر
    0.68
    Parcelize
    0.55
    onAttach
    0.50
    المصادر
    0.50
    GoogleApiClient
    0.50
    batore
    0.49
     disambiguazione
    0.49
    ChildScrollView
    0.49
    initas
    0.48
    WriteLiteral
    0.46
    Activations Density 0.269%

    No Known Activations