Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 14552
    Prev
    Next
    INDEX
    Explanations

    technical terms and acronyms related to technology and information systems

    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
    +0.18
    0.9%
    1339
    +0.10
    0.5%
    1363
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    845
    +0.18
    0.06
    1577
    +0.10
    0.07
    1539
    +0.09
    0.03
    Negative Logits
    <bos>
    -3.38
    ⓧ
    -1.16
     bezeichneter
    -0.98
    <?
    -0.95
     Walkover
    -0.91
    /**
    -0.90
    ɵɵelementEnd
    -0.83
    
    
    -0.83
    PCell
    -0.82
     himo
    -0.81
    POSITIVE LOGITS
     maneu
    2.32
     affor
    2.31
     increa
    2.29
     impra
    2.25
     shenan
    2.21
     disagre
    2.17
     reluct
    2.08
     scrat
    2.03
     unspeak
    2.01
     indestru
    2.00
    Activations Density 0.590%

    No Known Activations