© 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. 3701
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data analysis and statistical methods

    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
    227
    +0.20
    0.7%
    845
    +0.15
    0.6%
    62
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.20
    0.08
    845
    +0.15
    0.05
    62
    +0.12
    0.04
    Negative Logits
    IsContent
    -0.85
    PMailer
    -0.82
    DoubleQuotes
    -0.71
    aarrggbb
    -0.70
    <bos>
    -0.70
    reportWebVitals
    -0.69
    FailureListener
    -0.68
    enderror
    -0.68
    CodedInputStream
    -0.68
    RegressionTest
    -0.67
    POSITIVE LOGITS
     reluct
    1.49
     disagre
    1.46
     uninten
    1.46
     increa
    1.39
     affor
    1.36
     inev
    1.35
     inconce
    1.34
     impra
    1.34
     depic
    1.34
     emphat
    1.33
    Activations Density 0.848%

    No Known Activations