© 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. 14314
    Prev
    Next
    INDEX
    Explanations

    instances of specific actions, interactions, and conditions within a detailed narrative or story

    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
    1152
    +0.07
    0.2%
    1842
    +0.06
    0.2%
    2014
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.07
    0.04
    1533
    +0.06
    0.01
    736
    +0.06
    0.05
    Negative Logits
     erad
    -0.68
     atx
    -0.67
     poff
    -0.67
     bayern
    -0.66
     emend
    -0.65
     dsg
    -0.65
     wien
    -0.64
     franz
    -0.64
     suscep
    -0.64
     toledo
    -0.64
    POSITIVE LOGITS
     her
    0.81
     herself
    0.81
     husband
    0.72
     husbands
    0.68
     hubby
    0.67
    herself
    0.67
     chồng
    0.63
    URLException
    0.62
     boyfriend
    0.60
     male
    0.60
    Activations Density 0.483%

    No Known Activations