© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 940
    Prev
    Next
    INDEX
    Explanations

    text related to technical instructions for programming and data manipulation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    2019
    +0.33
    1.2%
    1535
    +0.23
    0.8%
    381
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.33
    0.10
    1535
    +0.23
    0.08
    924
    +0.16
    0.07
    Negative Logits
    Assista
    -0.77
     Zwar
    -0.76
    Característica
    -0.74
    Może
    -0.73
    Materiaal
    -0.73
    Conheça
    -0.72
    CARACTERÍSTICAS
    -0.72
    Dicas
    -0.72
    Galería
    -0.71
    Și
    -0.71
    POSITIVE LOGITS
     istan
    1.45
     maroc
    1.38
     fta
    1.36
     hej
    1.33
     mef
    1.32
     marte
    1.32
     milano
    1.32
     aen
    1.32
     jaya
    1.32
     meis
    1.32
    Activations Density 0.389%

    No Known Activations