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. 3362
    Prev
    Next
    INDEX
    Explanations

    variations of the verb "to be" in different contexts

    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
    providedIn
    -0.96
    AndEndTag
    -0.88
     للمعارف
    -0.87
    Geplaatst
    -0.84
    IntoConstraints
    -0.84
     <>",
    -0.83
    endphp
    -0.83
    InitVars
    -0.82
    TypedDataSet
    -0.81
    didSet
    -0.81
    POSITIVE LOGITS
     been
    0.66
    Been
    0.61
    一直
    0.60
     Been
    0.59
    ずっと
    0.53
     BEEN
    0.51
     бывает
    0.49
    我一直
    0.49
     stay
    0.47
     always
    0.46
    Activations Density 0.135%

    No Known Activations