© 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. 920
    Prev
    Next
    INDEX
    Explanations

    rich descriptive language related to the passage of time and personal reflection

    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
    872
    +0.10
    0.3%
    382
    +0.10
    0.3%
    1741
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1265
    +0.10
    0.06
    382
    +0.10
    0.06
    69
    +0.10
    0.03
    Negative Logits
     embra
    -1.40
     Keny
    -1.37
     increa
    -1.36
     secon
    -1.36
     antik
    -1.36
     mef
    -1.35
     deleter
    -1.35
     ivi
    -1.35
     uniqu
    -1.35
     igno
    -1.34
    POSITIVE LOGITS
     or
    0.70
     whether
    0.69
     또는
    0.68
     especially
    0.66
     but
    0.65
    ,
    0.63
     дори
    0.63
     maybe
    0.62
     그리고
    0.62
     like
    0.61
    Activations Density 0.306%

    No Known Activations