© 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. 5528
    Prev
    Next
    INDEX
    Explanations

    numbers and technical details

    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
    50
    +0.12
    0.4%
    1253
    +0.11
    0.3%
    776
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    609
    +0.12
    0.05
    776
    +0.11
    0.06
    1614
    +0.10
    0.06
    Negative Logits
     있으며
    -0.71
     있다
    -0.69
     있습니다
    -0.68
     just
    -0.68
     있는
    -0.66
     자신의
    -0.65
     된
    -0.65
    其
    -0.65
     upon
    -0.65
     ся
    -0.64
    POSITIVE LOGITS
     effe
    2.45
     guarante
    2.43
     emphat
    2.36
     increa
    2.33
     affor
    2.33
     wien
    2.31
     ?...
    2.31
     inev
    2.30
     accla
    2.30
     inder
    2.28
    Activations Density 0.453%

    No Known Activations