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

    Neuronpedia

    Jacobian LensNEW
    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. 5893
    Prev
    Next
    INDEX
    Explanations

    phrases related to police warnings or directions given during an arrest

    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
    1842
    +0.20
    0.6%
    1967
    +0.16
    0.5%
    674
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1265
    +0.20
    0.05
    1959
    +0.16
    0.06
    1445
    +0.14
    0.06
    Negative Logits
     fta
    -1.10
     umo
    -1.10
     hina
    -1.09
     ?...
    -1.08
     mef
    -1.07
     meis
    -1.06
     !...
    -1.05
     daz
    -1.04
     lele
    -1.04
     „,
    -1.04
    POSITIVE LOGITS
     but
    0.54
     you
    0.52
     etc
    0.52
     we
    0.52
     please
    0.52
     don
    0.51
     no
    0.50
     therefore
    0.50
     You
    0.47
     relax
    0.47
    Activations Density 0.437%

    No Known Activations