© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2104
    Prev
    Next
    INDEX
    Explanations

    references to Connecticut and its associated entities, specifically legal and governmental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1133
    +0.17
    0.9%
    1103
    +0.16
    0.9%
    241
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1133
    +0.17
    0.03
    227
    +0.16
    0.03
    648
    +0.14
    0.02
    Negative Logits
    <bos>
    -1.43
     disbur
    -0.59
     endow
    -0.58
     defray
    -0.58
     rehabilitate
    -0.58
    FTFY
    -0.56
     intersper
    -0.55
    <?
    -0.55
     unden
    -0.55
     négociations
    -0.53
    POSITIVE LOGITS
     Connecticut
    1.48
    Connecticut
    1.39
     CT
    1.27
     Hartford
    1.08
     Conn
    1.07
    cticut
    1.04
    CT
    1.03
    Hart
    0.92
    Conn
    0.88
     ct
    0.88
    Activations Density 0.111%

    No Known Activations