© 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. 13735
    Prev
    Next
    INDEX
    Explanations

    phrases related to social and political issues, particularly regarding constitutional reform and social justice advocacy

    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
    1533
    +0.11
    0.3%
    752
    +0.09
    0.3%
    599
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1270
    +0.11
    0.05
    1533
    +0.09
    0.02
    305
    +0.09
    0.04
    Negative Logits
     écrans
    -0.69
    YMMV
    -0.65
    idać
    -0.65
     ouvriers
    -0.63
     człowie
    -0.61
     juges
    -0.61
    Denote
    -0.60
     abriu
    -0.60
     bénévoles
    -0.60
     journalistes
    -0.60
    POSITIVE LOGITS
     perifer
    0.73
     Mâ
    0.71
     Luxem
    0.70
     Leopoldo
    0.69
     Chá
    0.68
     Jerusal
    0.67
     Praga
    0.67
     citizens
    0.66
     patin
    0.65
     Territor
    0.64
    Activations Density 0.415%

    No Known Activations