© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 4236
    Prev
    Next
    INDEX
    Explanations

    mentions of the baseball team "Rangers" and related players or trades

    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
    1145
    +0.17
    0.8%
    161
    +0.14
    0.6%
    32
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1145
    +0.17
    0.04
    732
    +0.14
    0.03
    981
    +0.13
    0.04
    Negative Logits
    Sucesor
    -0.56
    Τι
    -0.50
    GraphicsUnit
    -0.47
    Zü
    -0.46
    CodeAttribute
    -0.46
     jsPsych
    -0.45
    Bern
    -0.45
    デーション
    -0.44
    Σε
    -0.44
    accoon
    -0.44
    POSITIVE LOGITS
     Rangers
    1.22
     rangers
    1.14
     Ranger
    1.13
    Rangers
    1.11
     ranger
    1.09
    Ranger
    1.00
     Whence
    0.81
     apprehen
    0.80
     intersper
    0.79
     ROSS
    0.79
    Activations Density 0.273%

    No Known Activations