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. 0-RES-JB
    6. 2
    Prev
    Next
    INDEX
    Explanations

    information about financial reports, news events, and company-related content

    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
    +0.09
    0.3%
    501
    +0.07
    0.2%
    1872
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.09
    0.06
    1120
    +0.07
    0.05
    344
    +0.07
    0.04
    Negative Logits
    <bos>
    -0.94
    CLUSIVE
    -0.67
    USTAIN
    -0.63
    ostruct
    -0.62
    criptures
    -0.61
    toMatch
    -0.61
    couts
    -0.58
    RotationOrder
    -0.57
    phinx
    -0.56
    Rhestr
    -0.56
    POSITIVE LOGITS
     SB
    1.43
     véhic
    1.28
     affor
    1.21
     Sg
    1.21
     SF
    1.18
     soulign
    1.18
     SJ
    1.17
     Sf
    1.16
     Simult
    1.16
    SB
    1.15
    Activations Density 0.250%

    No Known Activations