© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14412
    Prev
    Next
    INDEX
    Explanations

    code snippets related to creating Ionic pages and services

    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
    876
    +0.18
    0.6%
    674
    +0.17
    0.5%
    453
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1511
    +0.18
    0.02
    876
    +0.17
    -0.00
    872
    +0.13
    0.04
    Negative Logits
     Ukraina
    -0.61
     Singapur
    -0.59
    Referencoj
    -0.59
    Avez
    -0.59
    Crítica
    -0.58
    Reparto
    -0.57
    Psico
    -0.56
    JComboBox
    -0.56
    Eksteraj
    -0.56
    Entrevista
    -0.56
    POSITIVE LOGITS
     scrat
    1.53
     peppa
    1.50
     lamborghini
    1.41
     tupperware
    1.41
     oreo
    1.35
     perfet
    1.33
     guarante
    1.32
     increa
    1.31
     affor
    1.30
     burberry
    1.30
    Activations Density 0.178%

    No Known Activations