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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14235
    Prev
    Next
    INDEX
    Explanations

    structured data containing numbers

    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
    674
    +0.44
    3.9%
    1741
    +0.07
    0.6%
    1042
    +0.04
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1403
    +0.44
    0.17
    15
    +0.07
    0.19
    674
    +0.04
    0.18
    Negative Logits
     despotism
    -1.18
     belliger
    -1.13
     massacres
    -1.10
     nukes
    -1.08
     ruinous
    -1.03
     Fascism
    -1.01
     demoral
    -1.01
     armaments
    -1.01
    Bullshit
    -1.00
     traitors
    -0.98
    POSITIVE LOGITS
    <bos>
    13.62
    expandindo
    2.42
    GEBURTSDATUM
    2.38
    Autoritní
    2.38
     betweenstory
    2.32
     kasarigan
    2.06
    تقاوى
    1.99
     Administrativna
    1.96
     Italijani
    1.94
     autorytatywna
    1.90
    Activations Density 0.078%

    No Known Activations