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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 6862
    Prev
    Next
    INDEX
    Explanations

    numbers, particularly those related to events or timelines

    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.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.16
    0.7%
    1978
    +0.15
    0.7%
    1708
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1614
    +0.16
    0.05
    1978
    +0.15
    0.04
    1527
    +0.12
    0.04
    Negative Logits
    <bos>
    -2.19
     abandon
    -0.61
     człowie
    -0.61
     reinstate
    -0.60
     (
    -0.59
     consider
    -0.59
     re
    -0.59
     continue
    -0.59
     me
    -0.59
     lengthen
    -0.58
    POSITIVE LOGITS
     maksi
    1.92
     lele
    1.91
     antik
    1.85
     alkoh
    1.82
     seksi
    1.80
     keramik
    1.76
     kafe
    1.75
     kristal
    1.74
     kram
    1.74
     panik
    1.69
    Activations Density 0.050%

    No Known Activations