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. 25-GEMMASCOPE-RES-16K
    6. 12485
    Prev
    Next
    INDEX
    Explanations

    phrases expressing personal responsibility and individual accountability

    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
     оригіналу
    -0.63
    ともに
    -0.63
    الدراسه
    -0.62
    bcryptjs
    -0.58
     également
    -0.57
     تضيفلها
    -0.56
     also
    -0.56
    (!__
    -0.55
     yani
    -0.53
    やはり
    -0.53
    POSITIVE LOGITS
     XYZ
    1.59
     xyz
    1.36
    XYZ
    1.23
     X
    1.19
     blah
    0.98
     x
    0.90
    〇〇
    0.89
    ○○
    0.89
     XY
    0.88
    X
    0.87
    Activations Density 0.865%

    No Known Activations