© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12478
    Prev
    Next
    INDEX
    Explanations

    references to acronyms and accompanying words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -1.02
    VIAF
    -1.01
     "..\..\
    -0.86
    RepeatedField
    -0.78
     Preferencias
    -0.78
    addPreferredGap
    -0.77
     evan
    -0.76
    Personendaten
    -0.76
    virons
    -0.76
     Byte
    -0.76
    POSITIVE LOGITS
     Ac
    1.06
    ac
    1.01
     ACCOM
    1.00
    AC
    0.99
     ACC
    0.97
    Acro
    0.90
    Ac
    0.90
    ACC
    0.89
     accredit
    0.89
     AC
    0.86
    Activations Density 0.142%

    No Known Activations