© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 679
    Prev
    Next
    INDEX
    Explanations

    references to specific company names

    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
    687
    +0.07
    0.2%
    966
    +0.07
    0.2%
    1604
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.07
    0.01
    1343
    +0.07
    0.03
    1363
    +0.07
    0.02
    Negative Logits
     arrived
    -0.56
    vertebrates
    -0.56
    теристика
    -0.56
     apparently
    -0.55
    bibfnamefont
    -0.55
     visited
    -0.55
     ruled
    -0.54
    ثيل
    -0.54
     pay
    -0.54
     happen
    -0.53
    POSITIVE LOGITS
    era
    2.65
    ERA
    1.87
     effe
    1.41
     unden
    1.40
     oner
    1.38
     unce
    1.35
     inder
    1.35
     squa
    1.34
     stockholm
    1.32
     aen
    1.31
    Activations Density 0.200%

    No Known Activations