© 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. 7360
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning specific numbers and measurements

    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
    1445
    +0.12
    0.3%
    198
    +0.09
    0.3%
    1252
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    741
    +0.12
    0.05
    198
    +0.09
    0.05
    1551
    +0.09
    0.04
    Negative Logits
     imagenes
    -0.47
    Attributes
    -0.44
     długość
    -0.42
     obreros
    -0.42
    Contexts
    -0.42
     :'(
    -0.41
    medik
    -0.40
    ImageName
    -0.40
     notwendigen
    -0.40
    투
    -0.39
    POSITIVE LOGITS
     Voyez
    0.97
     Áng
    0.92
     cytoplas
    0.91
     parteci
    0.91
     Darío
    0.90
     Valentín
    0.90
     Mejía
    0.86
     scopri
    0.85
     Ceux
    0.85
     Luglio
    0.83
    Activations Density 0.617%

    No Known Activations