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. 8-GEMMASCOPE-RES-16K
    6. 4763
    Prev
    Next
    INDEX
    Explanations

    phrases related to necessity or essential conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dymyr
    -0.89
    oliber
    -0.81
    ggior
    -0.80
    liflower
    -0.71
    ghurt
    -0.71
    ValueStyle
    -0.69
     chin
    -0.69
     mourir
    -0.69
     Poul
    -0.68
    Vtbl
    -0.68
    POSITIVE LOGITS
    Necessary
    1.44
     Necessary
    1.24
     necessary
    1.18
     necessity
    1.11
    必要
    1.08
     necessities
    1.08
    necessary
    1.06
     Necessity
    1.05
     NECESS
    1.02
    neces
    0.99
    Activations Density 0.081%

    No Known Activations