© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12393
    Prev
    Next
    INDEX
    Explanations

    information related to licenses for images and articles

    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
    1343
    +0.14
    0.4%
    185
    +0.09
    0.3%
    1135
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    841
    +0.14
    0.01
    1105
    +0.09
    0.02
    185
    +0.09
    0.01
    Negative Logits
    InjectMocks
    -0.73
     ModelExpression
    -0.71
    RegressionTest
    -0.68
    Hogyan
    -0.65
    Vlastnosti
    -0.62
    lhes
    -0.62
    MessageTagHelper
    -0.61
     بيها
    -0.60
    Warto
    -0.60
    (['/
    -0.60
    POSITIVE LOGITS
     overla
    1.12
     milano
    1.02
     dora
    1.01
     levis
    1.00
     espé
    0.99
     ordina
    0.98
     wien
    0.98
     ruota
    0.96
     sopr
    0.95
     effe
    0.95
    Activations Density 0.066%

    No Known Activations