© 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. 13774
    Prev
    Next
    INDEX
    Explanations

    terms related to the evolution of different subjects, including code, psychology, and political views

    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
    1379
    +0.13
    0.5%
    1865
    +0.12
    0.4%
    486
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1379
    +0.13
    0.03
    276
    +0.12
    0.03
    1865
    +0.10
    0.02
    Negative Logits
     Áng
    -0.68
     Rubén
    -0.57
     Justo
    -0.52
     Héctor
    -0.50
     Cabe
    -0.48
     Personne
    -0.48
     Compañ
    -0.46
     Lunes
    -0.45
     abriu
    -0.45
    frastructure
    -0.45
    POSITIVE LOGITS
     evolution
    1.18
     Evolution
    1.13
    evolution
    1.12
     evolu
    1.12
    Evolution
    1.11
     evolve
    1.11
     evolutionary
    0.99
     evolved
    0.96
    evolve
    0.96
     evolves
    0.95
    Activations Density 0.085%

    No Known Activations