© 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. 6-RES-JB
    11. 7064
    Prev
    Next
    INDEX
    Explanations

    references to logic and reasoning, especially in a textual or academic context

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.13
    0.6%
    144
    +0.13
    0.6%
    1085
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    144
    +0.13
    0.03
    699
    +0.13
    0.03
    1363
    +0.11
    0.03
    Negative Logits
    <bos>
    -2.25
     disambigu
    -0.71
    /***
    -0.62
     allude
    -0.61
     intersper
    -0.60
    Promote
    -0.58
     amass
    -0.55
     resemb
    -0.54
     contextes
    -0.54
     inaugurate
    -0.54
    POSITIVE LOGITS
     logic
    1.22
     Logic
    1.11
    logic
    1.06
    Logic
    1.05
     logical
    1.00
     thuy
    0.97
     logique
    0.92
     logica
    0.90
    LOGIC
    0.90
     bandung
    0.88
    Activations Density 0.181%

    No Known Activations