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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2143
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to political and military conflict, particularly involving terrorist organizations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1961
    +0.15
    0.6%
    1896
    +0.14
    0.6%
    1548
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.15
    0.11
    1896
    +0.14
    0.06
    1120
    +0.13
    0.08
    Negative Logits
    <bos>
    -1.00
    y
    -0.94
    s
    -0.91
    ی
    -0.88
    ه
    -0.87
    ה
    -0.83
    i
    -0.83
    o
    -0.82
    e
    -0.80
    я
    -0.78
    POSITIVE LOGITS
     increa
    2.36
     unden
    2.21
     fluo
    2.20
     stockholm
    2.16
     impra
    2.16
     unce
    2.16
     accla
    2.15
     effe
    2.13
     inev
    2.11
     excru
    2.11
    Activations Density 0.810%

    No Known Activations