© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1366
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to titles or headings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    597
    +0.12
    0.4%
    492
    +0.11
    0.3%
    1597
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.12
    0.04
    1363
    +0.11
    0.03
    690
    +0.08
    0.04
    Negative Logits
     shenan
    -1.51
     encomp
    -1.44
     cushi
    -1.38
     increa
    -1.34
     affor
    -1.31
     intersper
    -1.31
     disreg
    -1.25
     impra
    -1.23
     unspeak
    -1.23
     jorge
    -1.21
    POSITIVE LOGITS
     tit
    2.55
    tit
    2.41
     Tit
    2.38
    Tit
    2.33
    TIT
    1.72
     TIT
    1.56
     titu
    1.08
     tits
    0.92
    tits
    0.92
     titul
    0.90
    Activations Density 0.315%

    No Known Activations