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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 31
    Prev
    Next
    INDEX
    Explanations

    information related to technical instructions and troubleshooting for devices such as printers, generators, and computers

    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
    0.8%
    1385
    +0.10
    0.5%
    1438
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.18
    0.10
    1819
    +0.10
    0.07
    658
    +0.10
    0.07
    Negative Logits
    <bos>
    -3.14
     intersper
    -0.86
     endow
    -0.80
     disbur
    -0.79
     abate
    -0.77
     repress
    -0.76
     promul
    -0.76
     amass
    -0.75
     reconno
    -0.72
     cede
    -0.71
    POSITIVE LOGITS
    ">...
    0.95
     jawa
    0.85
    ">/
    0.84
     ecru
    0.79
     bandung
    0.77
     romero
    0.76
    >\<
    0.73
     Bekasi
    0.73
     quoc
    0.72
     Lampung
    0.72
    Activations Density 0.598%

    No Known Activations