© 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. 817
    Prev
    Next
    INDEX
    Explanations

    phrases related to governance and politics

    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
    764
    +0.09
    0.3%
    1705
    +0.08
    0.2%
    1314
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1705
    +0.09
    0.06
    1774
    +0.08
    0.03
    277
    +0.08
    0.03
    Negative Logits
    Solución
    -0.49
     orgánica
    -0.46
     kuto
    -0.44
    NOWLED
    -0.44
     pymysql
    -0.43
     oczywiście
    -0.43
    izumi
    -0.42
    sprüng
    -0.42
    onekana
    -0.42
     Ejec
    -0.41
    POSITIVE LOGITS
     thermomix
    1.05
     tetrach
    0.97
     fluo
    0.93
     oleo
    0.92
     stratigraph
    0.90
     anhyd
    0.88
     zirc
    0.83
     dolom
    0.81
     nephe
    0.81
     marl
    0.80
    Activations Density 0.620%

    No Known Activations