© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 981
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and technical concepts

    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
    674
    +0.46
    1.7%
    1967
    +0.14
    0.5%
    1438
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    779
    +0.46
    0.04
    184
    +0.14
    0.01
    284
    +0.10
    0.06
    Negative Logits
     unspeak
    -1.95
     impra
    -1.93
     increa
    -1.82
     unwarran
    -1.81
     shenan
    -1.80
     reluct
    -1.80
     tolerably
    -1.77
     indescri
    -1.76
     inev
    -1.75
     apprehen
    -1.74
    POSITIVE LOGITS
    <bos>
    2.58
    
    
    0.60
    /*!
    
    0.60
    LayoutConstraint
    0.54
    /**
    0.53
    <?
    0.52
     butterknife
    0.51
    Geplaatst
    0.51
    /*++
    0.50
    Jeografia
    0.50
    Activations Density 0.883%

    No Known Activations