© 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. 899
    Prev
    Next
    INDEX
    Explanations

    instances where something goes "bad" or is "broken"

    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
    468
    +0.16
    0.5%
    1842
    +0.13
    0.4%
    946
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.16
    0.07
    1531
    +0.13
    0.05
    1553
    +0.12
    0.06
    Negative Logits
     increa
    -0.93
     unlaw
    -0.91
     reluct
    -0.85
     Messieurs
    -0.84
     sappi
    -0.83
     fortn
    -0.83
     Perci
    -0.81
     volunte
    -0.81
     inev
    -0.80
     impractica
    -0.80
    POSITIVE LOGITS
     or
    0.91
     или
    0.76
     oder
    0.76
    或
    0.68
     eller
    0.68
    หรือ
    0.65
     یا
    0.63
    或者
    0.62
     nebo
    0.62
     或
    0.62
    Activations Density 0.607%

    No Known Activations