© 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. 3533
    Prev
    Next
    INDEX
    Explanations

    terms related to political figures, labor activities, and research projects

    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
    +0.12
    0.3%
    1385
    +0.10
    0.3%
    50
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1969
    +0.12
    0.04
    1202
    +0.10
    0.03
    168
    +0.09
    0.03
    Negative Logits
    ercice
    -0.66
    ),),
    -0.60
    emples
    -0.60
     człowie
    -0.57
    getreten
    -0.55
    zensionen
    -0.55
     tetrach
    -0.54
     hoffe
    -0.53
    ALLENG
    -0.53
     Aufl
    -0.53
    POSITIVE LOGITS
     viciss
    0.69
     Perci
    0.67
     Chá
    0.65
     Haci
    0.65
     Khart
    0.65
    Huhu
    0.64
     Darío
    0.63
     Tercera
    0.62
    Läh
    0.62
     Egli
    0.60
    Activations Density 0.170%

    No Known Activations