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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1134
    Prev
    Next
    INDEX
    Explanations

    phrases related to military operations against a specific threat

    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
    752
    +0.09
    0.2%
    604
    +0.09
    0.2%
    946
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    100
    +0.09
    0.05
    946
    +0.09
    0.05
    392
    +0.08
    0.03
    Negative Logits
    <bos>
    -1.10
     scrat
    -1.06
     snoopy
    -0.95
     impra
    -0.93
     unden
    -0.93
     cuck
    -0.91
     embra
    -0.89
     strick
    -0.88
     excru
    -0.88
     berea
    -0.87
    POSITIVE LOGITS
    PushMatrix
    0.67
     targets
    0.54
    chapper
    0.54
     suspected
    0.53
    inalg
    0.52
     ($("#
    0.51
     dangerous
    0.50
     remaining
    0.48
    Palmar
    0.48
     target
    0.47
    Activations Density 0.412%

    No Known Activations