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. 15030
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of people in various contexts

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

    Word fragments, potentially the ends of words

    np_acts-logits-general · gemini-2.0-flash

    parts of names

    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
    StoryboardSegue
    -0.96
    OGND
    -0.87
     виправивши
    -0.83
     الرياضيه
    -0.83
    uarts
    -0.83
     snippetHide
    -0.80
    InstrumentedTest
    -0.79
    原始内容存档于
    -0.78
    SOUNDBITE
    -0.77
     estekak
    -0.77
    POSITIVE LOGITS
    ’
    0.52
    ber
    0.51
    ha
    0.49
    ya
    0.49
    har
    0.45
    <em>
    0.45
    ra
    0.45
    As
    0.44
    ch
    0.44
    ​
    0.43
    Activations Density 0.141%

    No Known Activations