© 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. 13395
    Prev
    Next
    INDEX
    Explanations

    the phrase "it says."

    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
    1222
    +0.11
    0.3%
    1328
    +0.10
    0.3%
    421
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    82
    +0.11
    0.05
    1919
    +0.10
    0.06
    1328
    +0.10
    0.06
    Negative Logits
     pama
    -0.67
     Perci
    -0.66
     moza
    -0.65
     tén
    -0.65
     thermomix
    -0.65
     ferait
    -0.64
     monté
    -0.64
     dinosau
    -0.63
     Jä
    -0.63
     nmax
    -0.63
    POSITIVE LOGITS
     itself
    0.74
    Its
    0.72
     Its
    0.69
    itself
    0.67
    ]--;
    0.65
     its
    0.64
    its
    0.58
     Itself
    0.57
    它
    0.55
    ']>
    0.53
    Activations Density 0.426%

    No Known Activations