© 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. 5454
    Prev
    Next
    INDEX
    Explanations

    keywords related to data streaming and technical information

    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
    1328
    +0.18
    0.7%
    122
    +0.16
    0.7%
    101
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1425
    +0.18
    0.03
    1328
    +0.16
    0.03
    122
    +0.14
    0.02
    Negative Logits
     nobili
    -0.53
     dör
    -0.52
     republi
    -0.47
    DatabaseError
    -0.45
     palme
    -0.45
     respek
    -0.44
     randon
    -0.43
     Egyp
    -0.43
     kram
    -0.43
     asfal
    -0.42
    POSITIVE LOGITS
     stream
    1.45
     streams
    1.30
    stream
    1.30
     Stream
    1.29
    Stream
    1.19
     Streams
    1.17
     STREAM
    1.15
     streaming
    1.12
    streams
    1.11
     streamed
    1.08
    Activations Density 0.064%

    No Known Activations