© 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. 13919
    Prev
    Next
    INDEX
    Explanations

    years expressed in text form

    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
    +0.15
    0.4%
    559
    +0.13
    0.4%
    776
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.15
    0.06
    321
    +0.13
    0.05
    787
    +0.09
    0.04
    Negative Logits
     oleo
    -1.26
     casio
    -1.25
     michelin
    -1.25
     snoopy
    -1.17
     tupperware
    -1.13
     affor
    -1.13
     bougie
    -1.12
     vhs
    -1.08
     exorbit
    -1.08
     embodi
    -1.08
    POSITIVE LOGITS
    bonucle
    0.62
    /*
    0.62
    UVWXYZ
    0.57
    ]=="
    0.54
    obacz
    0.53
     snippetHide
    0.52
    ]>=
    0.52
    rscheinlichkeit
    0.52
    цуз
    0.51
    coroutines
    0.51
    Activations Density 0.135%

    No Known Activations