© 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. 3642
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic trade agreements and policies

    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
    394
    +0.30
    1.1%
    856
    +0.20
    0.8%
    184
    +0.17
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.30
    0.01
    394
    +0.20
    0.02
    163
    +0.17
    0.01
    Negative Logits
     reluct
    -1.50
     volunte
    -1.50
     accla
    -1.47
     practition
    -1.46
     philanth
    -1.44
     depic
    -1.42
     emphat
    -1.40
     sovere
    -1.38
     Juf
    -1.36
     Intere
    -1.36
    POSITIVE LOGITS
    <bos>
    0.96
    BoxShadow
    0.58
     often
    0.54
    Dichloropropane
    0.54
     ErrIntOverflow
    0.53
    CascadeType
    0.52
     usually
    0.51
     provide
    0.50
     straips
    0.50
    RectangleBorder
    0.49
    Activations Density 0.095%

    No Known Activations