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-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 8526
    Prev
    Next
    INDEX
    Explanations

    underscores, indicating a focus on formatting or structure in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     queſta
    -1.51
     ſind
    -1.50
     laſſen
    -1.37
     faſt
    -1.30
    majánló
    -1.29
    <unused51>
    -1.28
    <unused52>
    -1.28
    <unused28>
    -1.28
    <unused14>
    -1.28
    <unused23>
    -1.28
    POSITIVE LOGITS
    _
    2.19
    \_
    1.23
    _{
    1.09
     _
    0.99
    -
    0.96
    <bos>
    0.91
    /
    0.85
    __
    0.84
    }_
    0.83
    <sub>
    0.81
    Activations Density 0.805%

    No Known Activations