© 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. 1965
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of individuals

    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
    1296
    +0.09
    0.2%
    855
    +0.09
    0.2%
    1304
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.09
    0.06
    283
    +0.09
    0.02
    184
    +0.07
    0.03
    Negative Logits
     chemok
    -0.51
    ırl
    -0.50
     kõ
    -0.49
    itects
    -0.49
     tõ
    -0.49
    فة
    -0.48
     pres
    -0.48
    クロ
    -0.48
     speelt
    -0.48
    nio
    -0.47
    POSITIVE LOGITS
     Diana
    1.33
    iki
    1.28
     sappi
    1.26
     diana
    1.23
    Diana
    1.21
     kram
    1.18
     blin
    1.16
     utop
    1.14
     ohr
    1.13
     logis
    1.11
    Activations Density 0.432%

    No Known Activations