© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 3462
    Prev
    Next
    INDEX
    Explanations

    alternatives or different options

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1323
    +0.15
    0.5%
    1265
    +0.13
    0.5%
    316
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1323
    +0.15
    0.03
    316
    +0.13
    0.03
    1865
    +0.13
    0.02
    Negative Logits
    bufio
    -0.44
    LikeLike
    -0.43
    Hvad
    -0.42
    Doch
    -0.41
     Moh
    -0.40
    Dacă
    -0.39
    enada
    -0.39
    LikeLiked
    -0.39
    BorderFactory
    -0.39
     requestCode
    -0.39
    POSITIVE LOGITS
     Alternative
    1.07
     alternative
    1.06
     ALTERNATIVE
    1.03
    alternative
    1.02
    Alternative
    1.00
     alternatives
    0.96
    Alternatives
    0.91
     Alternatives
    0.89
     Alternate
    0.86
     alternate
    0.85
    Activations Density 0.072%

    No Known Activations