© 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. 13709
    Prev
    Next
    INDEX
    Explanations

    discussions about philosophical and political concepts like laws and beliefs

    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
    581
    +0.08
    0.2%
    1978
    +0.08
    0.2%
    1510
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    832
    +0.08
    0.05
    862
    +0.08
    0.02
    1919
    +0.07
    0.05
    Negative Logits
     ché
    -0.68
     idr
    -0.60
     buta
    -0.60
     ù
    -0.59
     mao
    -0.59
     zom
    -0.59
     alm
    -0.58
     piment
    -0.58
     º
    -0.57
     ria
    -0.57
    POSITIVE LOGITS
     anymore
    0.67
    znál
    0.66
     ever
    0.59
     ogóle
    0.57
     jemals
    0.56
     fared
    0.56
    ">...
    0.52
     whether
    0.52
     =[]
    0.52
     perchance
    0.50
    Activations Density 0.440%

    No Known Activations