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. 1835
    Prev
    Next
    INDEX
    Explanations

    references to the Nobel Prize and its recipients

    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
    251
    +0.14
    0.7%
    67
    +0.13
    0.6%
    1047
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.14
    0.02
    251
    +0.13
    0.02
    1798
    +0.12
    0.02
    Negative Logits
    <bos>
    -2.29
    BufferException
    -0.69
    RuleContext
    -0.68
     дописавши
    -0.68
    /**
    -0.66
    ValueGenerated
    -0.64
     maintain
    -0.63
    SharedCtor
    -0.61
     fly
    -0.60
     esternos
    -0.59
    POSITIVE LOGITS
     valencia
    1.37
     santiago
    1.32
     Nobel
    1.20
     toledo
    1.20
     Minang
    1.20
     roberto
    1.19
     noel
    1.16
    Nobel
    1.15
     tramont
    1.15
     fernando
    1.14
    Activations Density 0.073%

    No Known Activations