© 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. 1820
    Prev
    Next
    INDEX
    Explanations

    information about significant achievements or leadership roles in legal, investigative, or social contexts

    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
    1177
    +0.10
    0.3%
    2047
    +0.08
    0.2%
    344
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1038
    +0.10
    0.04
    16
    +0.08
    0.06
    652
    +0.07
    0.05
    Negative Logits
     betweenstory
    -0.60
    ItemBackground
    -0.54
     worin
    -0.51
     فريبيس
    -0.51
    <bos>
    -0.51
    нъ
    -0.50
    GORITHM
    -0.50
    done
    -0.49
    uses
    -0.49
    StatusCodes
    -0.49
    POSITIVE LOGITS
     maneu
    1.50
     shenan
    1.40
     fortn
    1.37
     Augu
    1.36
     wherea
    1.35
     increa
    1.34
     impra
    1.31
     secon
    1.30
     dises
    1.30
     Juf
    1.29
    Activations Density 0.414%

    No Known Activations