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. 1-GEMMASCOPE-RES-16K
    6. 13664
    Prev
    Next
    INDEX
    Explanations

    references to mentorship and faith

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endphp
    -0.90
     AttributeSet
    -0.71
     htons
    -0.70
    SequentialGroup
    -0.70
     SEDS
    -0.63
    WriteLiteral
    -0.60
    AddAttribute
    -0.59
    deelte
    -0.59
     androidx
    -0.59
    brenner
    -0.58
    POSITIVE LOGITS
     mentor
    1.81
     mentors
    1.70
     Mentor
    1.60
     mentoring
    1.49
    Mentor
    1.49
     mentorship
    1.41
     Mentoring
    1.36
    mentor
    1.21
     Ment
    1.04
    Ment
    1.03
    Activations Density 0.130%

    No Known Activations