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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11557
    Prev
    Next
    INDEX
    Explanations

    instances of the word "across"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
    theless
    -0.43
    ]
    -0.39
    il
    -0.36
    1
    -0.36
    date
    -0.35
    ्य
    -0.35
    <bos>
    -0.34
    ful
    -0.34
    it
    -0.34
    Note
    -0.33
    POSITIVE LOGITS
     across
    1.17
     ACROSS
    1.15
    across
    1.13
     Across
    1.09
    Across
    1.06
     cross
    0.96
    cross
    0.90
     CROSS
    0.86
     tartalomajánló
    0.84
     Crosse
    0.84
    Activations Density 0.070%

    No Known Activations