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. 899
    Prev
    Next
    INDEX
    Explanations

    phrases indicating personal identity and self-description

    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
     themselves
    -1.05
     yourselves
    -0.90
    themselves
    -0.89
     serem
    -0.85
    檚
    -0.75
    CloseOperation
    -0.67
     Are
    -0.66
    Are
    -0.65
     yourself
    -0.64
     fossero
    -0.63
    POSITIVE LOGITS
     am
    2.16
     was
    1.24
     have
    1.21
    am
    1.05
     Am
    1.03
    Am
    1.01
     can
    0.99
     AM
    0.96
     will
    0.94
     don
    0.93
    Activations Density 0.332%

    No Known Activations