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. 14-GEMMASCOPE-RES-16K
    6. 4104
    Prev
    Next
    INDEX
    Explanations

    the start of new sections or paragraphs in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     McColl
    -0.77
    помним
    -0.76
    drück
    -0.71
     McCle
    -0.69
     Briggs
    -0.68
     Bewußt
    -0.67
    windowFixed
    -0.67
     McCa
    -0.65
     Matti
    -0.64
     McClure
    -0.63
    POSITIVE LOGITS
    hline
    2.31
    hdashline
    0.90
     Wallflower
    0.82
     []:
    0.79
    WriteBarrier
    0.75
     Harlow
    0.74
     Khrushchev
    0.73
    .*")]
    0.72
    }")]
    0.72
    rfloor
    0.71
    Activations Density 0.008%

    No Known Activations