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. 21-GEMMASCOPE-RES-16K
    6. 6342
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically apostrophes and quotation marks, indicating a focus on dialogue or possessive forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     “
    -1.05
     "
    -0.96
    “
    -0.92
    {}".
    -0.92
    ]["
    -0.90
    ("
    -0.85
    }}"
    -0.84
    {}",
    -0.83
    ,“
    -0.83
    >("
    -0.82
    POSITIVE LOGITS
     '
    1.56
     ‘
    1.52
    、『
    1.40
    ==='
    1.34
     ‚
    1.33
    |'
    1.28
    ...'
    1.25
     (‘
    1.24
    =’
    1.22
    。『
    1.19
    Activations Density 0.244%

    No Known Activations