© 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. 5990
    Prev
    Next
    INDEX
    Explanations

    words related to national parks and recreational areas

    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
    +0.22
    0.8%
    855
    +0.08
    0.3%
    1438
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    855
    +0.22
    0.05
    1120
    +0.08
    0.02
    320
    +0.07
    0.04
    Negative Logits
    <bos>
    -2.11
    
    -1.10
    <?
    -1.00
    ⓧ
    -0.97
    /**
    -0.88
     unve
    -0.80
     quitted
    -0.76
    <?
    -0.74
     shivered
    -0.74
     shuddered
    -0.72
    POSITIVE LOGITS
     AppBundle
    0.59
    ("")
    0.53
     padang
    0.53
    omenclature
    0.53
     échou
    0.53
     testé
    0.52
     InkWell
    0.50
    °-
    0.49
     coû
    0.49
     expériment
    0.49
    Activations Density 0.470%

    No Known Activations