© 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. 14180
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terms related to physical principles and concepts, particularly in the context of space and physics

    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
    876
    +0.20
    0.6%
    764
    +0.15
    0.5%
    50
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    872
    +0.20
    0.11
    1959
    +0.15
    0.11
    764
    +0.13
    0.07
    Negative Logits
     solidar
    -0.80
     Palestina
    -0.78
     kompati
    -0.76
     Jerusal
    -0.73
     ideolog
    -0.72
     Widodo
    -0.71
     Unito
    -0.71
     meras
    -0.71
     alkoh
    -0.70
     pesta
    -0.69
    POSITIVE LOGITS
     embodi
    1.33
     impractica
    1.25
     disagre
    1.19
     unwarran
    1.19
     unlaw
    1.13
     friable
    1.11
     pylab
    1.09
     impra
    1.09
     hairc
    1.08
     disreg
    1.08
    Activations Density 1.697%

    No Known Activations