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. 17-GEMMASCOPE-RES-16K
    6. 6018
    Prev
    Next
    INDEX
    Explanations

    text elements that mark the beginning of a new section or indicate emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '}>
    -0.70
    ]")]
    -0.68
    !’
    -0.64
    )$}
    -0.63
    存于互联网档案馆
    -0.63
    PathVariable
    -0.59
    tvguidetime
    -0.59
    ’).
    -0.58
     my
    -0.57
    ̍
    -0.56
    POSITIVE LOGITS
     your
    1.16
     yourself
    1.02
    your
    1.01
     you
    0.94
    Your
    0.84
     youre
    0.83
     Your
    0.81
    yourself
    0.79
    you
    0.71
    你自己
    0.69
    Activations Density 0.618%

    No Known Activations