© 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. 13742
    Prev
    Next
    INDEX
    Explanations

    contact information such as addresses and phone numbers

    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
    2019
    +0.28
    0.8%
    381
    +0.13
    0.4%
    924
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.28
    0.11
    924
    +0.13
    0.10
    536
    +0.11
    0.07
    Negative Logits
    rektur
    -0.57
     truk
    -0.55
    INERY
    -0.53
    oneph
    -0.53
    tilizer
    -0.52
    Assista
    -0.50
     etti
    -0.50
    Significado
    -0.49
    ांकि
    -0.49
    转发
    -0.49
    POSITIVE LOGITS
     embra
    1.12
     dispen
    1.06
     lts
    1.03
     fep
    1.01
     squa
    1.00
     apparti
    0.97
     wherea
    0.96
     fte
    0.96
     milf
    0.95
     fuf
    0.95
    Activations Density 0.502%

    No Known Activations