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. 9079
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence or acknowledgment of evidence and facts

    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
     Majefty
    -0.84
    ReusableCell
    -0.81
    Билгалдахарш
    -0.81
     Monfieur
    -0.81
     /\.
    -0.79
     ويكيميديا
    -0.79
     mergeFrom
    -0.77
    fjspx
    -0.76
     fubject
    -0.75
     ſche
    -0.74
    POSITIVE LOGITS
     no
    0.64
     considerable
    0.54
     agreement
    0.51
     significant
    0.50
     agree
    0.50
     direct
    0.49
     agreed
    0.49
     also
    0.48
    stantial
    0.48
     concern
    0.47
    Activations Density 0.320%

    No Known Activations