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. 25-GEMMASCOPE-RES-16K
    6. 8626
    Prev
    Next
    INDEX
    Explanations

    topics related to suicide and mental health crises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    だが
    -0.56
    だったが
    -0.56
    twimg
    -0.55
    ようだ
    -0.48
    +:+
    -0.47
    俺は
    -0.45
    tawan
    -0.44
    errHandler
    -0.44
    windowFixed
    -0.43
    ನ್ನ
    -0.42
    POSITIVE LOGITS
     your
    2.74
     you
    2.66
    your
    2.48
    Your
    2.18
    you
    2.17
     yourselves
    2.12
     Your
    2.11
     vous
    2.07
     yourself
    1.96
     yours
    1.95
    Activations Density 0.151%

    No Known Activations