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. 12-RES-JB
    6. 7780
    Prev
    Next
    INDEX
    Explanations

    references to the passage of time and personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.12.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    12
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.28
    0.9%
    776
    +0.13
    0.4%
    1926
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.28
    0.07
    1728
    +0.13
    0.04
    297
    +0.09
    0.05
    Negative Logits
    <bos>
    -2.41
    ⓧ
    -0.64
    glPushMatrix
    -0.55
    Descripció
    -0.54
    Склад
    -0.54
    glBegin
    -0.54
    hook
    -0.53
    glBindTexture
    -0.53
    glBind
    -0.51
    новништво
    -0.49
    POSITIVE LOGITS
     Minang
    1.24
     Bekasi
    1.21
     Tangerang
    1.19
     Palembang
    1.09
     Banjar
    1.08
     Jambi
    1.05
     Banten
    1.05
     Karang
    1.04
     Muhamma
    1.04
     Pekan
    1.04
    Activations Density 0.318%

    No Known Activations