© 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. 13874
    Prev
    Next
    INDEX
    Explanations

    complex sentences or passages with a formal tone

    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
    814
    +0.14
    0.5%
    1482
    +0.10
    0.3%
    680
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    814
    +0.14
    0.03
    680
    +0.10
    0.02
    645
    +0.10
    0.02
    Negative Logits
     Himo
    -0.54
    equila
    -0.50
    rália
    -0.48
     Ant
    -0.48
     Normdatei
    -0.47
    DMETHOD
    -0.47
    webElement
    -0.46
    Ka
    -0.45
    IntoConstraints
    -0.45
     ModelRenderer
    -0.45
    POSITIVE LOGITS
     disreg
    1.00
     unspeak
    0.85
     jorge
    0.82
     shenan
    0.82
     invin
    0.82
     rodriguez
    0.81
     affitto
    0.81
     excru
    0.79
     perfet
    0.78
     ricardo
    0.78
    Activations Density 0.081%

    No Known Activations