© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 6438
    Prev
    Next
    INDEX
    Explanations

    mentions of furniture, specifically wall beds and cupboards

    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
    650
    +0.24
    1.3%
    331
    +0.18
    1.0%
    1222
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    757
    +0.24
    0.05
    1896
    +0.18
    0.03
    1741
    +0.17
    -0.00
    Negative Logits
     philanth
    -0.99
     unspeak
    -0.89
     hoody
    -0.87
     impra
    -0.87
     intersper
    -0.83
     gild
    -0.81
     affor
    -0.80
     endeavouring
    -0.80
     disbur
    -0.79
     endeav
    -0.79
    POSITIVE LOGITS
     Murphy
    0.82
     Pine
    0.73
    Murphy
    0.72
    Pine
    0.71
     pine
    0.69
     Murray
    0.60
     Rs
    0.60
     mur
    0.60
    pano
    0.58
     Berger
    0.58
    Activations Density 0.514%

    No Known Activations