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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13335
    Prev
    Next
    INDEX
    Explanations

    terms related to legal matters or regulations

    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
    1870
    +0.18
    0.7%
    755
    +0.13
    0.5%
    1671
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    755
    +0.18
    0.04
    1512
    +0.13
    0.04
    1763
    +0.12
    0.04
    Negative Logits
    GeneratedCode
    -0.60
    twimg
    -0.58
    Gambas
    -0.51
    scriptId
    -0.51
     createSprite
    -0.48
    getItemId
    -0.48
     olímp
    -0.47
     GeoNames
    -0.46
    JspWriter
    -0.46
     يتيمه
    -0.46
    POSITIVE LOGITS
     LEGAL
    1.10
     legal
    1.10
    legal
    1.04
    Legal
    1.00
     Legal
    0.98
     légal
    0.95
    LEGAL
    0.92
     lega
    0.91
     Sinal
    0.86
     Augu
    0.83
    Activations Density 0.069%

    No Known Activations