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. 16-GEMMASCOPE-RES-16K
    6. 172
    Prev
    Next
    INDEX
    Explanations

    code structures and elements related to UI components in a programming context

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

    Follows specific code or programming strings

    np_acts-logits-general · gemini-2.0-flash

    of a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.66
    AsUp
    -0.63
    SpringBootTest
    -0.63
    UnusedPrivate
    -0.63
     createSlice
    -0.61
    PreferredItem
    -0.58
    ungk
    -0.58
    ImageContext
    -0.57
    SBATCH
    -0.57
    encodeWith
    -0.57
    POSITIVE LOGITS
     للمعارف
    0.63
     ExecuteAsync
    0.52
    íses
    0.51
    Qaeda
    0.49
    engar
    0.48
    Tikang
    0.47
    thâu
    0.47
     ()
    0.45
    __((
    0.45
     Widodo
    0.44
    Activations Density 0.076%

    No Known Activations