© 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. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 2447
    Prev
    Next
    INDEX
    Explanations

    terms related to taxes and financial 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
    1510
    +0.14
    0.5%
    2034
    +0.10
    0.3%
    468
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2044
    +0.14
    0.08
    284
    +0.10
    0.07
    1652
    +0.10
    0.06
    Negative Logits
     sappi
    -1.69
     sergio
    -1.54
     felipe
    -1.50
     alberto
    -1.48
     javier
    -1.44
     vogli
    -1.44
     jorge
    -1.43
     roberto
    -1.42
     ricardo
    -1.40
     Cfr
    -1.35
    POSITIVE LOGITS
    .
    0.79
     and
    0.78
    ,
    0.72
     or
    0.70
     for
    0.69
    ;
    0.68
     are
    0.68
     in
    0.66
     at
    0.66
     on
    0.65
    Activations Density 0.576%

    No Known Activations