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. 1-GEMMASCOPE-RES-16K
    6. 6222
    Prev
    Next
    INDEX
    Explanations

    instances of the word "knew" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     egli
    -0.55
    RequestMapping
    -0.50
     partid
    -0.47
    MutableLiveData
    -0.47
     commonly
    -0.46
     lecz
    -0.46
    baomidou
    -0.46
     Stapleton
    -0.45
     populi
    -0.44
     Global
    -0.44
    POSITIVE LOGITS
     know
    3.43
     knows
    3.29
    Know
    3.27
     Know
    3.25
    know
    3.19
     KNOW
    3.08
     knew
    3.08
    KNOW
    2.94
    knows
    2.85
     knowing
    2.83
    Activations Density 0.052%

    No Known Activations