© 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 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. 13181
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals or organizations

    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
    1343
    +0.15
    0.5%
    227
    +0.14
    0.4%
    1097
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.15
    0.11
    1097
    +0.14
    0.08
    227
    +0.13
    0.08
    Negative Logits
     
    -0.75
     d
    -0.72
    ...
    -0.72
     her
    -0.72
     no
    -0.72
     a
    -0.71
     so
    -0.70
     la
    -0.70
     to
    -0.70
     de
    -0.69
    POSITIVE LOGITS
     milano
    2.29
     cannes
    2.16
     bandung
    2.01
     tanga
    1.99
     napoli
    1.96
     marte
    1.96
     lele
    1.96
     sergio
    1.95
     jorge
    1.94
     casio
    1.94
    Activations Density 0.352%

    No Known Activations