© 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. 3720
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings and investigations

    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
    1577
    +0.21
    0.7%
    184
    +0.17
    0.6%
    674
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1510
    +0.21
    0.04
    1156
    +0.17
    0.03
    1577
    +0.16
    0.05
    Negative Logits
     keramik
    -0.93
     monaster
    -0.93
     guir
    -0.84
     alkoh
    -0.82
     karton
    -0.81
     meras
    -0.79
     Chambres
    -0.79
     Leurs
    -0.78
     manuten
    -0.76
     LIRE
    -0.75
    POSITIVE LOGITS
     thereupon
    0.88
     impelled
    0.86
     unspeak
    0.85
     vainly
    0.82
     unavoid
    0.81
     apprehen
    0.77
     endeavouring
    0.77
     furthermore
    0.74
     ineffec
    0.74
     endeavoured
    0.72
    Activations Density 0.248%

    No Known Activations