© 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. 7536
    Prev
    Next
    INDEX
    Explanations

    references to work-related activities or achievements

    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
    1350
    +0.15
    0.5%
    144
    +0.12
    0.4%
    1993
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1993
    +0.15
    0.05
    144
    +0.12
    0.04
    169
    +0.11
    0.04
    Negative Logits
     psychiat
    -0.48
     verkle
    -0.47
    shafen
    -0.46
     Neustadt
    -0.45
    enfone
    -0.44
     akade
    -0.44
     abf
    -0.44
     zyn
    -0.43
    ENIX
    -0.43
    braio
    -0.43
    POSITIVE LOGITS
     work
    1.18
    work
    1.17
    Work
    1.16
     Work
    1.15
     WORK
    1.06
    WORK
    1.00
     Worked
    0.91
     peppa
    0.85
     works
    0.84
     unwarran
    0.83
    Activations Density 0.114%

    No Known Activations