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. 5704
    Prev
    Next
    INDEX
    Explanations

    descriptions of natural scenes and environments

    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
    1343
    +0.17
    0.8%
    1499
    +0.15
    0.7%
    381
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.17
    0.06
    1213
    +0.15
    0.03
    1291
    +0.12
    0.02
    Negative Logits
    <bos>
    -2.57
     intersper
    -1.24
     amass
    -0.90
     endow
    -0.90
     rouse
    -0.83
     banish
    -0.82
    <?
    -0.80
     disambigu
    -0.80
     quitted
    -0.79
     endeavored
    -0.77
    POSITIVE LOGITS
    :"-
    0.91
     véhic
    0.90
     quoique
    0.87
     soulign
    0.85
    %";
    0.83
     compét
    0.82
     Almería
    0.79
    öyle
    0.78
    %")
    0.77
     légiti
    0.76
    Activations Density 0.175%

    No Known Activations