© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 4187
    Prev
    Next
    INDEX
    Explanations

    quotes or reported speech

    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
    2019
    +0.27
    1.1%
    1757
    +0.20
    0.8%
    82
    +0.19
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    545
    +0.27
    0.11
    1404
    +0.20
    0.11
    82
    +0.19
    0.09
    Negative Logits
     COMPOUNDS
    -0.58
     '*':
    -0.54
     '/':
    -0.54
     '-':
    -0.53
     CONDU
    -0.49
     PHOSPH
    -0.49
     CHLOR
    -0.48
     HÀ
    -0.47
     bra
    -0.47
    inalg
    -0.46
    POSITIVE LOGITS
    ...."
    0.84
    leanor
    0.81
     Molto
    0.80
     viciss
    0.79
     pamph
    0.78
     practition
    0.78
    dison
    0.77
    ...'
    0.76
     ..."
    0.75
    #"
    0.75
    Activations Density 0.480%

    No Known Activations