© 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. 3775
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to container technology and software development

    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
    1842
    +0.42
    1.5%
    1577
    +0.27
    1.0%
    1870
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1842
    +0.42
    0.12
    1577
    +0.27
    0.10
    678
    +0.13
    0.07
    Negative Logits
    <bos>
    -1.15
     Shakspeare
    -0.92
     liberality
    -0.90
     endeavouring
    -0.80
     McLaugh
    -0.79
     Inhabitants
    -0.76
     unlaw
    -0.75
     Wtf
    -0.75
     Engraved
    -0.73
     unwarran
    -0.73
    POSITIVE LOGITS
     adal
    1.13
     utop
    1.13
     gesta
    1.10
     lomb
    1.09
     frans
    1.08
     reputa
    1.08
     vort
    1.08
     ristor
    1.07
     sement
    1.04
     toscana
    1.04
    Activations Density 1.256%

    No Known Activations