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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6438
    Prev
    Next
    INDEX
    Explanations

    power dynamics related to societal roles and behaviors

    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
    604
    +0.16
    0.5%
    198
    +0.09
    0.3%
    1368
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    779
    +0.16
    0.05
    100
    +0.09
    0.05
    16
    +0.08
    0.07
    Negative Logits
    <bos>
    -1.25
     kompati
    -0.59
    脚注の使い方
    -0.58
     calum
    -0.57
     decisivo
    -0.54
     rente
    -0.54
     comprends
    -0.53
     déchir
    -0.53
     honn
    -0.52
     incompet
    -0.52
    POSITIVE LOGITS
     negative
    0.60
     aggressive
    0.57
     destructive
    0.57
    negative
    0.56
     harmful
    0.56
     darker
    0.56
     abrasive
    0.55
     malicious
    0.53
     negatives
    0.52
     setError
    0.52
    Activations Density 0.937%

    No Known Activations