© 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. 3521
    Prev
    Next
    INDEX
    Explanations

    references to police actions and protests in a context of conflict

    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
    946
    +0.16
    0.5%
    1150
    +0.09
    0.3%
    378
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.16
    0.04
    1819
    +0.09
    0.04
    1018
    +0.09
    0.03
    Negative Logits
    Viitteet
    -0.66
     sò
    -0.61
     pép
    -0.60
    OGND
    -0.60
     LUMI
    -0.59
     intrig
    -0.59
     BNE
    -0.58
     grà
    -0.57
    MergeFrom
    -0.57
     ivelany
    -0.56
    POSITIVE LOGITS
     spray
    0.89
     sprayed
    0.88
     sprays
    0.77
     pymysql
    0.76
     spraying
    0.76
     intersper
    0.70
     tenté
    0.69
     refusé
    0.66
     smtplib
    0.65
    relenting
    0.64
    Activations Density 0.179%

    No Known Activations