© 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. 2491
    Prev
    Next
    INDEX
    Explanations

    mentions of biblical scripture and religious teachings related to evangelism and spreading the gospel

    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
    1343
    +0.15
    0.4%
    1380
    +0.11
    0.3%
    2015
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1612
    +0.15
    0.01
    89
    +0.11
    0.01
    150
    +0.09
    0.00
    Negative Logits
     reluct
    -1.82
     intersper
    -1.73
     unspeak
    -1.72
     shenan
    -1.71
     inconce
    -1.69
     disagre
    -1.68
     encomp
    -1.59
     caprice
    -1.59
     depic
    -1.59
     unwarran
    -1.59
    POSITIVE LOGITS
     Paglinawan
    0.78
    ponses
    0.77
    <bos>
    0.77
     Foire
    0.76
    Referencie
    0.70
    Filmografie
    0.67
    Einzelnachweise
    0.67
    Πηγές
    0.66
    Jegyzetek
    0.66
    }>;
    0.64
    Activations Density 0.037%

    No Known Activations