© 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. 13781
    Prev
    Next
    INDEX
    Explanations

    information related to mathematical calculations and procedures

    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
    876
    +0.18
    0.5%
    453
    +0.11
    0.3%
    1385
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.18
    -0.01
    1553
    +0.11
    0.04
    563
    +0.10
    0.03
    Negative Logits
     unspeak
    -1.00
     Shakspeare
    -0.96
     gaily
    -0.94
     pamph
    -0.92
     beaute
    -0.89
     tolerably
    -0.88
     shewn
    -0.86
     indescri
    -0.85
     withal
    -0.83
     endeavouring
    -0.83
    POSITIVE LOGITS
     sum
    0.72
     subtracting
    0.71
    sum
    0.64
     subtract
    0.63
     calculated
    0.63
     multiplied
    0.59
     numerator
    0.58
    Sum
    0.57
     sums
    0.57
     cộng
    0.56
    Activations Density 0.308%

    No Known Activations