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. 22-GEMMASCOPE-RES-16K
    6. 8101
    Prev
    Next
    INDEX
    Explanations

    terms related to conditions or actions that invoke a decision or requirement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding "be" (to be)

    np_acts-logits-general · gemini-2.0-flash

    to be verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.82
    setViewportView
    -0.81
    BASEPATH
    -0.75
    ToAction
    -0.73
    RegistryLite
    -0.72
    ]")]
    -0.72
    ोंने
    -0.72
    Rhestr
    -0.71
    SPATH
    -0.70
     createSlice
    -0.69
    POSITIVE LOGITS
     be
    1.75
     being
    1.72
     être
    1.59
    被
    1.49
     být
    1.49
     been
    1.47
     essere
    1.42
    being
    1.41
    Being
    1.34
     Being
    1.31
    Activations Density 1.668%

    No Known Activations