© 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. 14492
    Prev
    Next
    INDEX
    Explanations

    numeric figures and dates related to financial information

    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
    489
    +0.12
    0.4%
    442
    +0.12
    0.4%
    568
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.12
    0.06
    382
    +0.12
    0.06
    1343
    +0.12
    0.06
    Negative Logits
     bourgeo
    -0.84
     viciss
    -0.77
     impractica
    -0.74
     Czechos
    -0.71
     depic
    -0.70
     pamph
    -0.69
     underval
    -0.67
     Diener
    -0.66
     resear
    -0.66
     ecclesias
    -0.66
    POSITIVE LOGITS
    Chỉ
    0.47
    JOR
    0.43
     TIEMPO
    0.43
    Chúng
    0.42
    Benzene
    0.42
    Làm
    0.42
    grill
    0.41
    Điện
    0.41
     Doğ
    0.41
     TRAB
    0.41
    Activations Density 0.273%

    No Known Activations