© 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 EvalsExportsinterp-engineNEWAPI 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. 5134
    Prev
    Next
    INDEX
    Explanations

    phrases related to local breweries and craft beer production

    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
    505
    +0.09
    0.2%
    1823
    +0.08
    0.2%
    478
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1823
    +0.09
    0.03
    1086
    +0.08
    0.03
    1207
    +0.08
    0.03
    Negative Logits
     Juf
    -1.53
     maneu
    -1.48
     reluct
    -1.46
     shenan
    -1.41
     increa
    -1.40
     strick
    -1.39
     disagre
    -1.38
     impra
    -1.38
     fta
    -1.38
     suscep
    -1.38
    POSITIVE LOGITS
    <bos>
    0.76
     extra
    0.64
     valuable
    0.63
    FontOfSize
    0.62
     potentially
    0.60
     chance
    0.60
     boost
    0.60
    AndEndTag
    0.59
     endblock
    0.59
     access
    0.58
    Activations Density 0.436%

    No Known Activations