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

    Neuronpedia

    Jacobian LensNEW
    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. 5912
    Prev
    Next
    INDEX
    Explanations

    phrases indicating opinions or predictions using specific language patterns

    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
    47
    +0.13
    0.4%
    528
    +0.09
    0.3%
    410
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.13
    0.05
    1101
    +0.09
    0.03
    1454
    +0.09
    0.03
    Negative Logits
     NUKAT
    -0.49
     بتاريخ
    -0.47
    carol
    -0.44
     Kluwer
    -0.43
    rH
    -0.41
    Lr
    -0.41
     Instrum
    -0.41
    Models
    -0.40
    cS
    -0.40
     Oldenburg
    -0.40
    POSITIVE LOGITS
     abbra
    0.76
     pecuni
    0.74
     nutella
    0.69
     churrasco
    0.68
     ritard
    0.67
     ideolog
    0.66
     intende
    0.64
     Siamo
    0.64
     ridu
    0.64
     sappi
    0.64
    Activations Density 0.145%

    No Known Activations