Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 4456
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly single quotes and parentheses

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

    Single quotation marks

    np_acts-logits-general · gemini-2.0-flash

    string delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "
    -1.06
     ("
    -0.90
     “
    -0.88
    ]["
    -0.82
    {}".
    -0.79
    ("
    -0.79
    /"
    -0.78
    >("
    -0.76
    -"
    -0.75
     "";
    -0.74
    POSITIVE LOGITS
     ‘
    1.46
    、『
    1.35
     '
    1.30
    ...'
    1.29
    …’
    1.24
    |'
    1.20
     (‘
    1.16
    。『
    1.14
    『
    1.13
    =’
    1.13
    Activations Density 0.170%

    No Known Activations