© 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. 4665
    Prev
    Next
    INDEX
    Explanations

    words related to the Islamic State of Iraq and the Levant (ISIL or ISIS)

    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
    765
    +0.13
    0.5%
    1984
    +0.12
    0.4%
    1870
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    765
    +0.13
    0.04
    492
    +0.12
    0.03
    1677
    +0.12
    0.03
    Negative Logits
     CascadeType
    -0.59
    HttpPut
    -0.51
    fjspx
    -0.51
    deepEqual
    -0.51
     Proben
    -0.49
    нодоро
    -0.47
    marginHorizontal
    -0.46
    obut
    -0.46
    orElseThrow
    -0.46
    FieldNumber
    -0.45
    POSITIVE LOGITS
     Islamic
    1.01
     Rine
    1.00
     Mlle
    1.00
     McLaugh
    0.99
     Daven
    0.99
    Islamic
    0.98
     Intere
    0.91
     Godt
    0.88
     Mónica
    0.88
     Augu
    0.88
    Activations Density 0.040%

    No Known Activations