© 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. 0-RES-JB
    11. 645
    Prev
    Next
    INDEX
    Explanations

    references to time, specifically focusing on the concept of 'time' as an important element within the text

    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
    50
    +0.12
    0.5%
    1113
    +0.06
    0.2%
    1438
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1053
    +0.12
    0.03
    1839
    +0.06
    0.03
    1045
    +0.06
    0.03
    Negative Logits
    <bos>
    -1.86
    ⓧ
    -0.70
     banish
    -0.70
     hasten
    -0.67
     reinstate
    -0.65
    
    -0.65
     neutralize
    -0.64
    /**
    -0.64
     subdue
    -0.63
     disbur
    -0.63
    POSITIVE LOGITS
     véhic
    0.95
     maroc
    0.86
     ados
    0.85
     mikrofon
    0.83
     pleins
    0.83
     silikon
    0.83
     toscana
    0.81
    capulco
    0.81
     montagna
    0.79
     Minang
    0.76
    Activations Density 0.140%

    No Known Activations