© 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. 3501
    Prev
    Next
    INDEX
    Explanations

    URLs and technical references related to mental health and philosophy

    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
    227
    +0.17
    0.5%
    1343
    +0.15
    0.4%
    1380
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.17
    0.05
    227
    +0.15
    0.05
    924
    +0.12
    0.04
    Negative Logits
     ruine
    -0.87
     regardant
    -0.78
     Vainqueur
    -0.78
     Californie
    -0.77
     cinquante
    -0.77
     Docteur
    -0.75
     Barcelone
    -0.75
     Messieurs
    -0.75
    🕗
    -0.75
     Amiens
    -0.75
    POSITIVE LOGITS
    online
    0.62
    ERICA
    0.58
    inc
    0.57
     maravill
    0.56
    web
    0.55
    info
    0.54
     unie
    0.53
    @
    0.53
    here
    0.53
     apasion
    0.53
    Activations Density 0.128%

    No Known Activations