© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12599
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contrast or options

    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
    1472
    +0.15
    0.5%
    1328
    +0.14
    0.5%
    1842
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1806
    +0.15
    0.09
    1472
    +0.14
    0.07
    1127
    +0.14
    0.06
    Negative Logits
    apnews
    -0.57
    Denomin
    -0.52
    TextSpan
    -0.51
    MessageWindow
    -0.51
    XCTAssertEqual
    -0.50
    Lepid
    -0.50
    FunctionFlags
    -0.50
     Walkover
    -0.49
    GEBRA
    -0.48
    HtmlAttribute
    -0.48
    POSITIVE LOGITS
     disagre
    1.33
     encomp
    1.26
     shenan
    1.24
     apprehen
    1.23
     quitted
    1.20
     uninten
    1.19
     gaily
    1.19
     reluct
    1.17
     impra
    1.16
     increa
    1.14
    Activations Density 0.252%

    No Known Activations