© 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. 718
    Prev
    Next
    INDEX
    Explanations

    text related to thermal activities such as thermal parks, pools, springs, and treatments

    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
    410
    +0.11
    0.3%
    1256
    +0.09
    0.3%
    1909
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    809
    +0.11
    0.03
    410
    +0.09
    0.02
    192
    +0.09
    0.02
    Negative Logits
     Kab
    -0.54
     sit
    -0.53
    세
    -0.53
     أعلام
    -0.52
    gu
    -0.52
     ha
    -0.52
     came
    -0.52
    ,
    -0.51
     store
    -0.51
     hit
    -0.51
    POSITIVE LOGITS
     thermal
    2.83
     Thermal
    2.70
    Thermal
    2.57
    thermal
    2.48
     thermally
    2.04
     therm
    1.74
     thermo
    1.67
     THER
    1.63
     Thermo
    1.46
     Therm
    1.45
    Activations Density 0.197%

    No Known Activations