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. 12698
    Prev
    Next
    INDEX
    Explanations

    biological terms and labels related to genetic sequences and mutations

    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
    n
    -1.19
    k
    -1.14
    t
    -1.09
    r
    -1.07
    l
    -1.07
    m
    -1.02
    ng
    -0.96
    p
    -0.95
    ling
    -0.95
    s
    -0.94
    POSITIVE LOGITS
    tvguidetime
    1.18
    annica
    1.15
     LDA
    1.08
    drawal
    1.07
    esterday
    1.06
    łucha
    1.04
    polation
    1.02
    intenance
    1.02
    HSA
    1.01
     NTA
    1.01
    Activations Density 0.970%

    No Known Activations