© 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. 347
    Prev
    Next
    INDEX
    Explanations

    names or titles prefixed with 'Sir'

    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
    645
    +0.17
    0.9%
    50
    +0.12
    0.6%
    555
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    645
    +0.17
    0.03
    1677
    +0.12
    0.02
    1404
    +0.11
    0.02
    Negative Logits
    <bos>
    -2.46
    ⓧ
    -0.74
    <?
    -0.67
    /*++
    -0.66
    lateinit
    -0.62
    hline
    -0.61
    Παραπομπές
    -0.61
     poveznice
    -0.58
    
    -0.57
    <!--
    -0.57
    POSITIVE LOGITS
     Sir
    1.47
    Sir
    1.44
     sir
    1.32
     SIR
    1.28
     délib
    1.19
    SIR
    1.14
     véhic
    1.13
    sir
    1.09
     bayern
    1.09
     sergio
    1.09
    Activations Density 0.121%

    No Known Activations